Search

In recent years, large language models (LLMs) have been widely adopted in political science tasks such as election prediction, sentiment analysis, policy impact assessment, and misinformation detection. Meanwhile, the need to systematically understand how LLMs can further revolutionize the field also becomes urgent. In this work, we--a multidisciplinary team of researchers spanning computer science and political science--present the first principled framework termed Political-LLM to advance the comprehensive understanding of integrating LLMs into computational political science. Specifically, we first introduce a fundamental taxonomy classifying the existing explorations into two perspectives: political science and computational methodologies. In particular, from the political science perspective, we highlight the role of LLMs in automating predictive and generative tasks, simulating behavior dynamics, and improving causal inference through tools like counterfactual generation; from a computational perspective, we introduce advancements in data preparation, fine-tuning, and evaluation methods for LLMs that are tailored to political contexts. We identify key challenges and future directions, emphasizing the development of domain-specific datasets, addressing issues of bias and fairness, incorporating human expertise, and redefining evaluation criteria to align with the unique requirements of computational political science. Political-LLM seeks to serve as a guidebook for researchers to foster an informed, ethical, and impactful use of Artificial Intelligence in political science. Our online resource is available at: http://political-llm.org/., Comment: 54 Pages, 9 Figures

Gaussian splatting has gained attention for its efficient representation and rendering of 3D scenes using continuous Gaussian primitives. However, it struggles with sparse-view inputs due to limited geometric and photometric information, causing ambiguities in depth, shape, and texture. we propose GBR: Generative Bundle Refinement, a method for high-fidelity Gaussian splatting and meshing using only 4-6 input views. GBR integrates a neural bundle adjustment module to enhance geometry accuracy and a generative depth refinement module to improve geometry fidelity. More specifically, the neural bundle adjustment module integrates a foundation network to produce initial 3D point maps and point matches from unposed images, followed by bundle adjustment optimization to improve multiview consistency and point cloud accuracy. The generative depth refinement module employs a diffusion-based strategy to enhance geometric details and fidelity while preserving the scale. Finally, for Gaussian splatting optimization, we propose a multimodal loss function incorporating depth and normal consistency, geometric regularization, and pseudo-view supervision, providing robust guidance under sparse-view conditions. Experiments on widely used datasets show that GBR significantly outperforms existing methods under sparse-view inputs. Additionally, GBR demonstrates the ability to reconstruct and render large-scale real-world scenes, such as the Pavilion of Prince Teng and the Great Wall, with remarkable details using only 6 views.

Graphical overlays that layer visual elements onto charts, are effective to convey insights and context in financial narrative visualizations. However, automating graphical overlays is challenging due to complex narrative structures and limited understanding of effective overlays. To address the challenge, we first summarize the commonly used graphical overlays and narrative structures, and the proper correspondence between them in financial narrative visualizations, elected by a survey of 1752 layered charts with corresponding narratives. We then design FinFlier, a two-stage innovative system leveraging a knowledge-grounding large language model to automate graphical overlays for financial visualizations. The text-data binding module enhances the connection between financial vocabulary and tabular data through advanced prompt engineering, and the graphics overlaying module generates effective overlays with narrative sequencing. We demonstrate the feasibility and expressiveness of FinFlier through a gallery of graphical overlays covering diverse financial narrative visualizations. Performance evaluations and user studies further confirm system's effectiveness and the quality of generated layered charts., Comment: 17 pages, 13 figures, this paper is published on IEEE Transactions on Visualization and Computer Graphics

We are concerned with the compressible barotropic Navier--Stokes equations for a $\gamma$-law gas with density-dependent bulk viscosity coefficient $\lambda=\lambda(\rho)=\rho^\beta$ on the two-dimensional periodic domain $\mathbb{T}^2$. The global existence of weak solutions with initial density bounded away from zero and infinity for $\beta>3$, $\gamma>1$ has been established by Va\u{\i}gant--Kazhikhov [Sib. Math. J. 36 (1995), 1283--1316]. When $\gamma=\beta>3$, the large-time behaviour of the weak solutions and, in particular, the absence of formation of vacuum and concentration of density as $t \to \infty$, has been proved by Perepelitsa [SIAM J. Math. Anal. 39 (2007/08), 1344--1365]. Huang--Li [J. Math. Pures Appl. 106 (2016), 123--154] extended these results by establishing the global existence of weak solutions and large-time behaviour under the assumptions $\beta >3/2$, $1< \gamma<4\beta-3$, and that the initial density stays away from infinity (but may contain vacuum). Improving upon the works listed above, we prove that in the regime of parameters as in Huang--Li, namely that $\beta >3/2$ and $1< \gamma<4\beta-3$, if the density has no vacuum or concentration at $t=0$, then it stays uniformly away from zero and infinity at all later time $t \in ]0,\infty]$. Moreover, under the mere assumption that $\beta>1$ and $\gamma>1$, we establish the global existence of weak solutions, thus pushing the global existence theory of the barotropic Navier--Stokes equations on $\mathbb{T}^2$ to the most general setting to date. One of the key ingredients of our proof is a novel application -- motivated by the recent work due to Danchin--Mucha [Comm. Pure Appl. Math. 76 (2023), 3437--3492] -- of Desjardins' logarithmic interpolation inequality., Comment: 35 pages

Event cameras record visual information as asynchronous pixel change streams, excelling at scene perception under unsatisfactory lighting or high-dynamic conditions. Existing multimodal large language models (MLLMs) concentrate on natural RGB images, failing in scenarios where event data fits better. In this paper, we introduce EventGPT, the first MLLM for event stream understanding, to the best of our knowledge, marking a pioneering attempt to integrate large language models (LLMs) with event stream comprehension. To mitigate the huge domain gaps, we develop a three-stage optimization paradigm to gradually equip a pre-trained LLM with the capability of understanding event-based scenes. Our EventGPT comprises an event encoder, followed by a spatio-temporal aggregator, a linear projector, an event-language adapter, and an LLM. Firstly, RGB image-text pairs generated by GPT are leveraged to warm up the linear projector, referring to LLaVA, as the gap between natural image and language modalities is relatively smaller. Secondly, we construct a synthetic yet large dataset, N-ImageNet-Chat, consisting of event frames and corresponding texts to enable the use of the spatio-temporal aggregator and to train the event-language adapter, thereby aligning event features more closely with the language space. Finally, we gather an instruction dataset, Event-Chat, which contains extensive real-world data to fine-tune the entire model, further enhancing its generalization ability. We construct a comprehensive benchmark, and experiments show that EventGPT surpasses previous state-of-the-art MLLMs in generation quality, descriptive accuracy, and reasoning capability.

Combining the complementary benefits of frames and events has been widely used for object detection in challenging scenarios. However, most object detection methods use two independent Artificial Neural Network (ANN) branches, limiting cross-modality information interaction across the two visual streams and encountering challenges in extracting temporal cues from event streams with low power consumption. To address these challenges, we propose HDI-Former, a Hybrid Dynamic Interaction ANN-SNN Transformer, marking the first trial to design a directly trained hybrid ANN-SNN architecture for high-accuracy and energy-efficient object detection using frames and events. Technically, we first present a novel semantic-enhanced self-attention mechanism that strengthens the correlation between image encoding tokens within the ANN Transformer branch for better performance. Then, we design a Spiking Swin Transformer branch to model temporal cues from event streams with low power consumption. Finally, we propose a bio-inspired dynamic interaction mechanism between ANN and SNN sub-networks for cross-modality information interaction. The results demonstrate that our HDI-Former outperforms eleven state-of-the-art methods and our four baselines by a large margin. Our SNN branch also shows comparable performance to the ANN with the same architecture while consuming 10.57$\times$ less energy on the DSEC-Detection dataset. Our open-source code is available in the supplementary material., Comment: 17 pages, 11 figures

AIGC images are prevalent across various fields, yet they frequently suffer from quality issues like artifacts and unnatural textures. Specialized models aim to predict defect region heatmaps but face two primary challenges: (1) lack of explainability, failing to provide reasons and analyses for subtle defects, and (2) inability to leverage common sense and logical reasoning, leading to poor generalization. Multimodal large language models (MLLMs) promise better comprehension and reasoning but face their own challenges: (1) difficulty in fine-grained defect localization due to the limitations in capturing tiny details; and (2) constraints in providing pixel-wise outputs necessary for precise heatmap generation. To address these challenges, we propose HEIE: a novel MLLM-Based Hierarchical Explainable image Implausibility Evaluator. We introduce the CoT-Driven Explainable Trinity Evaluator, which integrates heatmaps, scores, and explanation outputs, using CoT to decompose complex tasks into subtasks of increasing difficulty and enhance interpretability. Our Adaptive Hierarchical Implausibility Mapper synergizes low-level image features with high-level mapper tokens from LLMs, enabling precise local-to-global hierarchical heatmap predictions through an uncertainty-based adaptive token approach. Moreover, we propose a new dataset: Expl-AIGI-Eval, designed to facilitate interpretable implausibility evaluation of AIGC images. Our method demonstrates state-of-the-art performance through extensive experiments.

The success of deep neural networks has driven numerous research studies and applications from Euclidean to non-Euclidean data. However, there are increasing concerns about privacy leakage, as these networks rely on processing private data. Recently, a new type of privacy attack, the model inversion attacks (MIAs), aims to extract sensitive features of private data for training by abusing access to a well-trained model. The effectiveness of MIAs has been demonstrated in various domains, including images, texts, and graphs. These attacks highlight the vulnerability of neural networks and raise awareness about the risk of privacy leakage within the research community. Despite the significance, there is a lack of systematic studies that provide a comprehensive overview and deeper insights into MIAs across different domains. This survey aims to summarize up-to-date MIA methods in both attacks and defenses, highlighting their contributions and limitations, underlying modeling principles, optimization challenges, and future directions. We hope this survey bridges the gap in the literature and facilitates future research in this critical area. Besides, we are maintaining a repository to keep track of relevant research at https://github.com/AndrewZhou924/Awesome-model-inversion-attack., Comment: 40 pages, 17 figures

Accurate modeling of terrestrial carbon and water exchange requires robust ecological parameters that capture vegetation responses and adaptations to the local environment. The current generation of land models use Plant Functional Types (PFTs) to discretize vegetation functional diversity, but these coarse categorizations often overlook fine-scale variations shaped by local climate, soil, and forest age factors. The lack of governing equations for plant adaptation demands a paradigm shift in how we integrate diverse Earth observations to uncover ecological functional dependence on changing environments. To address this challenge, we developed DifferLand, a differentiable, hybrid physics and machine learning model that infers the spatial distributions of ecological parameters and their relationships with environmental factors constrained by satellite and in-situ observations. Our model unifies top-down and bottom-up observational constraints with process-based knowledge to generate a global analysis of ecological functions and their adaptation to environmental gradients. We found PFTs account for less than half of the explainable spatial parameter variations controlling carbon fluxes and vegetation states. The remaining parameter variability is largely driven by local climate and forest demography factors, and the learned environment-parameter relationships lead to enhanced spatial generalization at unseen locations. DifferLand identified growing season length, leaf economics, and agricultural intensity as the three orthogonal spatial gradients underlying parameter variations. Our novel framework can lead to new insights on global carbon cycling by learning directly from data and expanding our understanding of local responses of ecosystems to environmental drivers.

Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, including API misuse and different attacks. Various studies have proposed backdoor-based watermarking schemes to protect the copyright of EaaS services. In this paper, we reveal that previous watermarking schemes possess semantic-independent characteristics and propose the Semantic Perturbation Attack (SPA). Our theoretical and experimental analyses demonstrate that this semantic-independent nature makes current watermarking schemes vulnerable to adaptive attacks that exploit semantic perturbations test to bypass watermark verification. To address this vulnerability, we propose the Semantic Aware Watermarking (SAW) scheme, a robust defense mechanism designed to resist SPA, by injecting a watermark that adapts to the text semantics. Extensive experimental results across multiple datasets demonstrate that the True Positive Rate (TPR) for detecting watermarked samples under SPA can reach up to more than 95%, rendering previous watermarks ineffective. Meanwhile, our watermarking scheme can resist such attack while ensuring the watermark verification capability. Our code is available at https://github.com/Zk4-ps/EaaS-Embedding-Watermark.

Handling lengthy context is crucial for enhancing the recognition and understanding capabilities of multimodal large language models (MLLMs) in applications such as processing high-resolution images or high frame rate videos. The rise in image resolution and frame rate substantially increases computational demands due to the increased number of input tokens. This challenge is further exacerbated by the quadratic complexity with respect to sequence length of the self-attention mechanism. Most prior works either pre-train models with long contexts, overlooking the efficiency problem, or attempt to reduce the context length via downsampling (e.g., identify the key image patches or frames) to decrease the context length, which may result in information loss. To circumvent this issue while keeping the remarkable effectiveness of MLLMs, we propose a novel approach using a hybrid transformer-MAMBA model to efficiently handle long contexts in multimodal applications. Our multimodal model can effectively process long context input exceeding 100k tokens, outperforming existing models across various benchmarks. Remarkably, our model enhances inference efficiency for high-resolution images and high-frame-rate videos by about 4 times compared to current models, with efficiency gains increasing as image resolution or video frames rise. Furthermore, our model is the first to be trained on low-resolution images or low-frame-rate videos while being capable of inference on high-resolution images and high-frame-rate videos, offering flexibility for inference in diverse scenarios.

As a prominent subfield of Artificial Intelligence Generated Content (AIGC), video generation has achieved notable advancements in recent years. The introduction of Sora-alike models represents a pivotal breakthrough in video generation technologies, significantly enhancing the quality of synthesized videos. Particularly in the realm of biomedicine, video generation technology has shown immense potential such as medical concept explanation, disease simulation, and biomedical data augmentation. In this article, we thoroughly examine the latest developments in video generation models and explore their applications, challenges, and future opportunities in the biomedical sector. We have conducted an extensive review and compiled a comprehensive list of datasets from various sources to facilitate the development and evaluation of video generative models in biomedicine. Given the rapid progress in this field, we have also created a github repository to regularly update the advances of biomedical video generation at: https://github.com/Lee728243228/Biomedical-Video-Generation

Out-of-distribution (OOD) detection is crucial for deploying reliable machine learning models in open-world applications. Recent advances in CLIP-based OOD detection have shown promising results via regularizing prompt tuning with OOD features extracted from ID data. However, the irrelevant context mined from ID data can be spurious due to the inaccurate foreground-background decomposition, thus limiting the OOD detection performance. In this work, we propose a novel framework, namely, Self-Calibrated Tuning (SCT), to mitigate this problem for effective OOD detection with only the given few-shot ID data. Specifically, SCT introduces modulating factors respectively on the two components of the original learning objective. It adaptively directs the optimization process between the two tasks during training on data with different prediction uncertainty to calibrate the influence of OOD regularization, which is compatible with many prompt tuning based OOD detection methods. Extensive experiments and analyses have been conducted to characterize and demonstrate the effectiveness of the proposed SCT. The code is publicly available., Comment: accepted by NeurIPS 2024

Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, these representations cannot effectively ignore any task-irrelevant information in the scene, and (2) They often lack the representational capacity to handle unconstrained/complex real-world scenes. Instead, we propose to train a large combinatorial family of representations organized by scene entities: objects and object parts. This hierarchical object decomposition for task-oriented representations (HODOR) permits selectively assembling different representations specific to each task while scaling in representational capacity with the complexity of the scene and the task. In our experiments, we find that HODOR outperforms prior pre-trained representations, both scene vector representations and object-centric representations, for sample-efficient imitation learning across 5 simulated and 5 real-world manipulation tasks. We further find that the invariances captured in HODOR are inherited into downstream policies, which can robustly generalize to out-of-distribution test conditions, permitting zero-shot skill chaining. Appendix, code, and videos: https://sites.google.com/view/hodor-corl24.

In real-world scenarios, it is desirable for embodied agents to have the ability to leverage human language to gain explicit or implicit knowledge for learning tasks. Despite recent progress, most previous approaches adopt simple low-level instructions as language inputs, which may not reflect natural human communication. It's not clear how to incorporate rich language use to facilitate task learning. To address this question, this paper studies different types of language inputs in facilitating reinforcement learning (RL) embodied agents. More specifically, we examine how different levels of language informativeness (i.e., feedback on past behaviors and future guidance) and diversity (i.e., variation of language expressions) impact agent learning and inference. Our empirical results based on four RL benchmarks demonstrate that agents trained with diverse and informative language feedback can achieve enhanced generalization and fast adaptation to new tasks. These findings highlight the pivotal role of language use in teaching embodied agents new tasks in an open world. Project website: https://github.com/sled-group/Teachable_RL, Comment: EMNLP 2024 Main. Project website: https://github.com/sled-group/Teachable_RL

This paper investigates an under-explored challenge in large language models (LLMs): chain-of-thought prompting with noisy rationales, which include irrelevant or inaccurate reasoning thoughts within examples used for in-context learning. We construct NoRa dataset that is tailored to evaluate the robustness of reasoning in the presence of noisy rationales. Our findings on NoRa dataset reveal a prevalent vulnerability to such noise among current LLMs, with existing robust methods like self-correction and self-consistency showing limited efficacy. Notably, compared to prompting with clean rationales, base LLM drops by 1.4%-19.8% in accuracy with irrelevant thoughts and more drastically by 2.2%-40.4% with inaccurate thoughts. Addressing this challenge necessitates external supervision that should be accessible in practice. Here, we propose the method of contrastive denoising with noisy chain-of-thought (CD-CoT). It enhances LLMs' denoising-reasoning capabilities by contrasting noisy rationales with only one clean rationale, which can be the minimal requirement for denoising-purpose prompting. This method follows a principle of exploration and exploitation: (1) rephrasing and selecting rationales in the input space to achieve explicit denoising and (2) exploring diverse reasoning paths and voting on answers in the output space. Empirically, CD-CoT demonstrates an average improvement of 17.8% in accuracy over the base model and shows significantly stronger denoising capabilities than baseline methods. The source code is publicly available at: https://github.com/tmlr-group/NoisyRationales., Comment: Accepted by NeurIPS 2024

Offline evaluation of LLMs is crucial in understanding their capacities, though current methods remain underexplored in existing research. In this work, we focus on the offline evaluation of the chain-of-thought capabilities and show how to optimize LLMs based on the proposed evaluation method. To enable offline feedback with rich knowledge and reasoning paths, we use knowledge graphs (e.g., Wikidata5m) to provide feedback on the generated chain of thoughts. Due to the heterogeneity between LLM reasoning and KG structures, direct interaction and feedback from KGs on LLM behavior are challenging, as they require accurate entity linking and grounding of LLM-generated chains of thought in the KG. To address the above challenge, we propose an offline chain-of-thought evaluation framework, OCEAN, which models chain-of-thought reasoning in LLMs as an MDP and evaluate the policy's alignment with KG preference modeling. To overcome the reasoning heterogeneity and grounding problems, we leverage on-policy KG exploration and RL to model a KG policy that generates token-level likelihood distributions for LLM-generated chain-of-thought reasoning paths, simulating KG reasoning preference. Then we incorporate the knowledge-graph feedback on the validity and alignment of the generated reasoning paths into inverse propensity scores and propose KG-IPS estimator. Theoretically, we prove the unbiasedness of the proposed KG-IPS estimator and provide a lower bound on its variance. With the off-policy evaluated value function, we can directly enable off-policy optimization to further enhance chain-of-thought alignment. Our empirical study shows that OCEAN can be efficiently optimized for generating chain-of-thought reasoning paths with higher estimated values without affecting LLMs' general abilities in downstream tasks or their internal knowledge., Comment: 10 pages

Hybrid spectral CT integrates energy integrating detectors (EID) and photon counting detectors (PCD) into a single system, combining the large field-of-view advantage of EID with the high energy and spatial resolution of PCD. This represents a new research direction in spectral CT imaging. However, the different imaging principles and inconsistent geometric paths of the two detectors make it difficult to reconstruct images using data from hybrid detectors. In addition, the quality reconstructed images considering spectrum is affected by the accuracy of spectral estimation and the scattered photons. In this work, Firstly, we propose a general hybrid spectral reconstruction method that takes into account both the spectral CT imaging principles of the two different detectors and the influence of scattered photons in the forward process modelling. Furthermore, we also apply volume fraction constraints to the results reconstructed from the two detector data. By alternately solving the spectral estimation and the spectral image reconstruction by the ADMM method, the estimated spectra and the reconstructed images reinforce each other, thus improving the accuracy of the spectral estimation and the quality of the reconstructed images. The proposed method is the first to achieve hybrid spectral CT reconstruction for both detectors, allowing simultaneous recovery of spectrum and image reconstruction from hybrid spectral data containing scattering. In addition, the method is also applicable to spectral CT imaging using a single type of detector. We validated the effectiveness of the proposed method through numerical experiments and successfully performed the first hybrid spectral CT reconstruction experiment on our self-developed hybrid spectral CT system.

Out-of-distribution (OOD) detection aims to identify OOD inputs from unknown classes, which is important for the reliable deployment of machine learning models in the open world. Various scoring functions are proposed to distinguish it from in-distribution (ID) data. However, existing methods generally focus on excavating the discriminative information from a single input, which implicitly limits its representation dimension. In this work, we introduce a novel perspective, i.e., employing different common corruptions on the input space, to expand that. We reveal an interesting phenomenon termed confidence mutation, where the confidence of OOD data can decrease significantly under the corruptions, while the ID data shows a higher confidence expectation considering the resistance of semantic features. Based on that, we formalize a new scoring method, namely, Confidence aVerage (CoVer), which can capture the dynamic differences by simply averaging the scores obtained from different corrupted inputs and the original ones, making the OOD and ID distributions more separable in detection tasks. Extensive experiments and analyses have been conducted to understand and verify the effectiveness of CoVer. The code is publicly available at: https://github.com/tmlr-group/CoVer., Comment: accepted by NeurIPS 2024

Explanation generation plays a more pivotal role than fact verification in producing interpretable results and facilitating comprehensive fact-checking, which has recently garnered considerable attention. However, previous studies on explanation generation has shown several limitations, such as being confined to English scenarios, involving overly complex inference processes, and not fully unleashing the potential of the mutual feedback between veracity labels and explanation texts. To address these issues, we construct two complex fact-checking datasets in the Chinese scenarios: CHEF-EG and TrendFact. These datasets involve complex facts in areas such as health, politics, and society, presenting significant challenges for fact verification methods. In response to these challenges, we propose a unified framework called FactISR (Augmenting Fact-Checking via Iterative Self-Revision) to perform mutual feedback between veracity and explanations by leveraging the capabilities of large language models(LLMs). FactISR uses a single model to address tasks such as fact verification and explanation generation. Its self-revision mechanism can further revision the consistency between veracity labels, explanation texts, and evidence, as well as eliminate irrelevant noise. We conducted extensive experiments with baselines and FactISR on the proposed datasets. The experimental results demonstrate the effectiveness of our method.

Antibodies are essential proteins responsible for immune responses in organisms, capable of specifically recognizing antigen molecules of pathogens. Recent advances in generative models have significantly enhanced rational antibody design. However, existing methods mainly create antibodies from scratch without template constraints, leading to model optimization challenges and unnatural sequences. To address these issues, we propose a retrieval-augmented diffusion framework, termed RADAb, for efficient antibody design. Our method leverages a set of structural homologous motifs that align with query structural constraints to guide the generative model in inversely optimizing antibodies according to desired design criteria. Specifically, we introduce a structure-informed retrieval mechanism that integrates these exemplar motifs with the input backbone through a novel dual-branch denoising module, utilizing both structural and evolutionary information. Additionally, we develop a conditional diffusion model that iteratively refines the optimization process by incorporating both global context and local evolutionary conditions. Our approach is agnostic to the choice of generative models. Empirical experiments demonstrate that our method achieves state-of-the-art performance in multiple antibody inverse folding and optimization tasks, offering a new perspective on biomolecular generative models.

Current LLM benchmarks focus on evaluating models' memory of facts and semantic relations, primarily assessing semantic aspects of long-term memory. However, in humans, long-term memory also includes episodic memory, which links memories to their contexts, such as the time and place they occurred. The ability to contextualize memories is crucial for many cognitive tasks and everyday functions. This form of memory has not been evaluated in LLMs with existing benchmarks. To address the gap in evaluating memory in LLMs, we introduce Sequence Order Recall Tasks (SORT), which we adapt from tasks used to study episodic memory in cognitive psychology. SORT requires LLMs to recall the correct order of text segments, and provides a general framework that is both easily extendable and does not require any additional annotations. We present an initial evaluation dataset, Book-SORT, comprising 36k pairs of segments extracted from 9 books recently added to the public domain. Based on a human experiment with 155 participants, we show that humans can recall sequence order based on long-term memory of a book. We find that models can perform the task with high accuracy when relevant text is given in-context during the SORT evaluation. However, when presented with the book text only during training, LLMs' performance on SORT falls short. By allowing to evaluate more aspects of memory, we believe that SORT will aid in the emerging development of memory-augmented models.

Recent advancements in test time compute, particularly through the use of verifier models, have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). This generator-verifier approach closely resembles the actor-critic framework in reinforcement learning (RL). However, current verifier models in LLMs often rely on supervised fine-tuning without temporal difference learning such as Q-learning. This paper introduces VerifierQ, a novel approach that integrates Offline Q-learning into LLM verifier models. We address three key challenges in applying Q-learning to LLMs: (1) handling utterance-level Markov Decision Processes (MDPs), (2) managing large action spaces, and (3) mitigating overestimation bias. VerifierQ introduces a modified Bellman update for bounded Q-values, incorporates Implicit Q-learning (IQL) for efficient action space management, and integrates a novel Conservative Q-learning (CQL) formulation for balanced Q-value estimation. Our method enables parallel Q-value computation and improving training efficiency. While recent work has explored RL techniques like MCTS for generators, VerifierQ is among the first to investigate the verifier (critic) aspect in LLMs through Q-learning. This integration of RL principles into verifier models complements existing advancements in generator techniques, potentially enabling more robust and adaptive reasoning in LLMs. Experimental results on mathematical reasoning tasks demonstrate VerifierQ's superior performance compared to traditional supervised fine-tuning approaches, with improvements in efficiency, accuracy and robustness. By enhancing the synergy between generation and evaluation capabilities, VerifierQ contributes to the ongoing evolution of AI systems in addressing complex cognitive tasks across various domains.

By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks, leveraging the robust architectures of Large Language Models (LLMs). However, as token counts grow, the quadratic scaling of computation in LLMs introduces a significant efficiency bottleneck, impeding further scalability. Although recent approaches have explored pruning visual tokens or employing lighter LLM architectures, the computational overhead from an increasing number of visual tokens remains a substantial challenge. In this study, we investigate the redundancy in visual computation at both the parameter and computational pattern levels within LLaVA, a representative MLLM, and introduce a suite of streamlined strategies to enhance efficiency. These include neighbor-aware visual token attention, pruning of inactive visual attention heads, and selective layer dropping for visual computations. By implementing these strategies in LLaVA, we achieve a reduction in computational demands of 88% while maintaining model performance across key benchmarks. Additionally, we validate the existence of visual computational redundancy in other MLLMs, such as Qwen2-VL-7B and InternVL-2.0-4B/8B/26B. These results present a novel pathway for MLLMs to handle dense visual tokens with minimal computational costs. Code and model checkpoints will be released to support further research.

With the rapid development of large language models (LLMs), their applications have expanded into diverse fields, such as code assistance. However, the substantial size of LLMs makes their training highly resource- and time-intensive, rendering frequent retraining or updates impractical. Consequently, time-sensitive data can become outdated, potentially misleading LLMs in time-aware tasks. For example, new vulnerabilities are discovered in various programs every day. Without updating their knowledge, LLMs may inadvertently generate code that includes these newly discovered vulnerabilities. Current strategies, such as prompt engineering and fine-tuning, do not effectively address this issue. To address this issue, we propose solution, named APILOT, which maintains a realtime, quickly updatable dataset of outdated APIs. Additionally, APILOT utilizes an augmented generation method that leverages this dataset to navigate LLMs in generating secure, version-aware code. We conducted a comprehensive evaluation to measure the effectiveness of APILOT in reducing the incidence of outdated API recommendations across seven different state-of-the-art LLMs. The evaluation results indicate that APILOT can reduce outdated code recommendations by 89.42% on average with limited performance overhead. Interestingly, while enhancing security, APILOT also improves the usability of the code generated by LLMs, showing an average increase of 27.54% in usability. This underscores APILOT's dual capability to enhance both the safety and practical utility of code suggestions in contemporary software development environments.

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat this issue, we present an \textbf{U}ncertainty-enhanced \textbf{P}reference \textbf{O}ptimization (UPO) framework to make the LLM self-evolve with reliable feedback. The key idea is mitigating the noisy preference data derived from the current policy and reward models by performing pair-wise uncertainty estimation and judiciously reliable feedback sampling. To reach this goal, we thus introduce an estimator model, which incorporates Monte Carlo (MC) dropout in Bayesian neural network (BNN) to perform uncertainty estimation for the preference data derived from the LLM policy. Compared to the existing methods that directly filter generated responses based on the reward score, the estimator focuses on the model uncertainty in a pair-wise manner and effectively bypasses the confirmation bias problem of the reward model. Additionally, we also propose an uncertainty-enhanced self-evolution algorithm to improve the robustness of preference optimization and encourage the LLM to generate responses with both high reward and certainty. Extensive experiments over multiple benchmarks demonstrate that our framework substantially alleviates the noisy problem and improves the performance of iterative preference optimization., Comment: 17 pages

We discusses the electromagnetic scattering and radiation problems of multilayered spheres, reviewing the historical expansion of the Lorentz-Mie theory and the numerical stability issues encountered in handling multilayered spheres. By combining recursive methods with the transfer matrix method, we propose a modified transfer matrix algorithm designed for the stable and efficient calculation of electromagnetic scattering coefficients of multilayered spheres. The new algorithm simplifies the recursive formulas by introducing Debye potentials and logarithmic derivatives, effectively avoiding numerical overflow issues associated with Bessel functions under large complex variables. Numerical test results demonstrate that this algorithm offers superior stability and applicability when dealing with complex cases such as thin shells and strongly absorbing media.

Reconstructing transmission networks is essential for identifying key factors like superspreaders and high-risk locations, which are critical for developing effective pandemic prevention strategies. In this study, we developed a Bayesian framework that integrates genomic and temporal data to reconstruct transmission networks for infectious diseases. The Bayesian transmission model accounts for the latent period and differentiates between symptom onset and actual infection time, enhancing the accuracy of transmission dynamics and epidemiological models. Additionally, the model allows for the transmission of multiple pathogen lineages, reflecting the complexity of real-world transmission events more accurately than models that assume a single lineage transmission. Simulation results show that the Bayesian model reliably estimates both the model parameters and the transmission network. Moreover, hypothesis testing effectively identifies direct transmission events. This approach highlights the crucial role of genetic data in reconstructing transmission networks and understanding the origins and transmission dynamics of infectious diseases.

This paper mainly investigates a class of distributed generalized Nash equilibrium (GNE) seeking problems for online nonmonotone game with time-varying coupling inequality constraints. Based on a time-varying control gain, a novel continuous-time distributed GNE seeking algorithm is proposed, which realizes the constant regret bound and sublinear fit bound, matching those of the criteria for online optimization problems. Furthermore, to reduce unnecessary communication among players, a dynamic event-triggered mechanism involving internal variables is introduced into the distributed GNE seeking algorithm, while the constant regret bound and sublinear fit bound are still achieved. Also, the Zeno behavior is strictly prohibited. Finally, a numerical example is given to demonstrate the validity of the theoretical results.

Today's top advertisers typically manage hundreds of campaigns simultaneously and consistently launch new ones throughout the year. A crucial challenge for marketing managers is determining the optimal allocation of limited budgets across various ad lines in each campaign to maximize cumulative returns, especially given the huge uncertainty in return outcomes. In this paper, we propose to formulate budget allocation as a multi-task combinatorial bandit problem and introduce a novel online budget allocation system. The proposed system: i) integrates a Bayesian hierarchical model to intelligently utilize the metadata of campaigns and ad lines and budget size, ensuring efficient information sharing; ii) provides the flexibility to incorporate diverse modeling techniques such as Linear Regression, Gaussian Processes, and Neural Networks, catering to diverse environmental complexities; and iii) employs the Thompson sampling (TS) technique to strike a balance between exploration and exploitation. Through offline evaluation and online experiments, our system demonstrates robustness and adaptability, effectively maximizing the overall cumulative returns. A Python implementation of the proposed procedure is available at https://anonymous.4open.science/r/MCMAB.

The exotic neutral gauge boson is a powerful candidate for the new physics beyond the standard model. As a promising model, the left-right symmetric model has been proposed to explain the neutrino mass, dark matter, and matter-antimatter asymmetry, etc., in which exotic gauge bosons $Z^\prime, W^{\prime \pm}$ have been put forward as well as other new right-handed particles. We investigate the $\mu^+ \mu^- \to q\bar{q} $ and $ \mu^+ \mu^- \to l^+ l^- $ processes involving the $Z^\prime$ boson as an intermediate particle. The coupling strength, decay width and mass are the key parameters on the production and decay processes of the $Z^\prime$ boson. The results indicate that the angular distributions of final particles are sensitive to the couplings of $Z^\prime$ to the other fermions. Asymmetries defined from the angular distributions are ideal quantities to demonstrate the discrepancy between the standard model process and the processes with $Z^\prime$ participated and they are also appropriate observables to discriminate the couplings of $Z^\prime$ to other particles. Compared with the current results at the Large Hadron Collider (LHC), the future muon collider has a great potential to explore the new parameter space with $Z^\prime$ boson., Comment: 22 pages, 10 figures

The Lunar landing has drawn great interest in lunar exploration in recent years, and autonomous lunar landing navigation is fundamental to this task. AI is expected to play a critical role in autonomous and intelligent space missions, yet human experts question the reliability of AI solutions. Thus, the \gls{xai} for vision-based lunar landing is studied in this paper, aiming at providing transparent and understandable predictions for intelligent lunar landing. Attention-based Darknet53 is proposed as the feature extraction structure. For crater detection and navigation tasks, attention-based YOLOv3 and attention-Darknet53-LSTM are presented respectively. The experimental results show that the offered networks provide competitive performance on relative crater detection and pose estimation during the lunar landing. The explainability of the provided networks is achieved by introducing an attention mechanism into the network during model building. Moreover, the PCC is utilised to quantitively evaluate the explainability of the proposed networks, with the findings showing the functions of various convolutional layers in the network.

Large language models (LLMs) have had a significant impact on diverse research domains, including medicine and healthcare. However, the potential of LLMs as copilots in medical education remains underexplored. Current AI-assisted educational tools are limited by their solitary learning approach and inability to simulate the multi-disciplinary and interactive nature of actual medical training. To address these limitations, we propose MEDCO (Medical EDucation COpilots), a novel multi-agent-based copilot system specially developed to emulate real-world medical training environments. MEDCO incorporates three primary agents: an agentic patient, an expert doctor, and a radiologist, facilitating a multi-modal and interactive learning environment. Our framework emphasizes the learning of proficient question-asking skills, multi-disciplinary collaboration, and peer discussions between students. Our experiments show that simulated virtual students who underwent training with MEDCO not only achieved substantial performance enhancements comparable to those of advanced models, but also demonstrated human-like learning behaviors and improvements, coupled with an increase in the number of learning samples. This work contributes to medical education by introducing a copilot that implements an interactive and collaborative learning approach. It also provides valuable insights into the effectiveness of AI-integrated training paradigms.

Sign Language Translation (SLT) is a core task in the field of AI-assisted disability. Unlike traditional SLT based on visible light videos, which is easily affected by factors such as lighting, rapid hand movements, and privacy breaches, this paper proposes the use of high-definition Event streams for SLT, effectively mitigating the aforementioned issues. This is primarily because Event streams have a high dynamic range and dense temporal signals, which can withstand low illumination and motion blur well. Additionally, due to their sparsity in space, they effectively protect the privacy of the target person. More specifically, we propose a new high-resolution Event stream sign language dataset, termed Event-CSL, which effectively fills the data gap in this area of research. It contains 14,827 videos, 14,821 glosses, and 2,544 Chinese words in the text vocabulary. These samples are collected in a variety of indoor and outdoor scenes, encompassing multiple angles, light intensities, and camera movements. We have benchmarked existing mainstream SLT works to enable fair comparison for future efforts. Based on this dataset and several other large-scale datasets, we propose a novel baseline method that fully leverages the Mamba model's ability to integrate temporal information of CNN features, resulting in improved sign language translation outcomes. Both the benchmark dataset and source code will be released on https://github.com/Event-AHU/OpenESL, Comment: First Large-scale and High-Definition Benchmark Dataset for Event-based Sign Language Translation

Financial time series modeling is crucial for understanding and predicting market behaviors but faces challenges such as non-linearity, non-stationarity, and high noise levels. Traditional models struggle to capture complex patterns due to these issues, compounded by limitations in computational resources and model capacity. Inspired by the success of large language models in NLP, we introduce $\textbf{PLUTUS}$, a $\textbf{P}$re-trained $\textbf{L}$arge $\textbf{U}$nified $\textbf{T}$ransformer-based model that $\textbf{U}$nveils regularities in financial time $\textbf{S}$eries. PLUTUS uses an invertible embedding module with contrastive learning and autoencoder techniques to create an approximate one-to-one mapping between raw data and patch embeddings. TimeFormer, an attention based architecture, forms the core of PLUTUS, effectively modeling high-noise time series. We incorporate a novel attention mechanisms to capture features across both variable and temporal dimensions. PLUTUS is pre-trained on an unprecedented dataset of 100 billion observations, designed to thrive in noisy financial environments. To our knowledge, PLUTUS is the first open-source, large-scale, pre-trained financial time series model with over one billion parameters. It achieves state-of-the-art performance in various tasks, demonstrating strong transferability and establishing a robust foundational model for finance. Our research provides technical guidance for pre-training financial time series data, setting a new standard in the field.

Myopia screening using cutting-edge ultra-widefield (UWF) fundus imaging and joint modeling of multiple discrete and continuous clinical scores presents a promising new paradigm for multi-task problems in Ophthalmology. The bi-channel framework that arises from the Ophthalmic phenomenon of ``interocular asymmetries'' of both eyes (OU) calls for new employment on the SOTA transformer-based models. However, the application of copula models for multiple mixed discrete-continuous labels on deep learning (DL) is challenging. Moreover, the application of advanced large transformer-based models to small medical datasets is challenging due to overfitting and computational resource constraints. To resolve these challenges, we propose OU-CoViT: a novel Copula-Enhanced Bi-Channel Multi-Task Vision Transformers with Dual Adaptation for OU-UWF images, which can i) incorporate conditional correlation information across multiple discrete and continuous labels within a deep learning framework (by deriving the closed form of a novel Copula Loss); ii) take OU inputs subject to both high correlation and interocular asymmetries using a bi-channel model with dual adaptation; and iii) enable the adaptation of large vision transformer (ViT) models to small medical datasets. Solid experiments demonstrate that OU-CoViT significantly improves prediction performance compared to single-channel baseline models with empirical loss. Furthermore, the novel architecture of OU-CoViT allows generalizability and extensions of our dual adaptation and Copula Loss to various ViT variants and large DL models on small medical datasets. Our approach opens up new possibilities for joint modeling of heterogeneous multi-channel input and mixed discrete-continuous clinical scores in medical practices and has the potential to advance AI-assisted clinical decision-making in various medical domains beyond Ophthalmology.

Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial purification in image classification tasks. However, such methods fall into the dilemma of balancing the needs for noise removal and information preservation. This paper points out that existing adversarial purification methods based on diffusion models gradually lose sample information during the core denoising process, causing occasional label shift in subsequent classification tasks. As a remedy, we suggest to suppress such information loss by introducing guidance from the classifier confidence. Specifically, we propose Classifier-cOnfidence gUided Purification (COUP) algorithm, which purifies adversarial examples while keeping away from the classifier decision boundary. Experimental results show that COUP can achieve better adversarial robustness under strong attack methods., Comment: Accepted by ECAI 2024

Off-policy evaluation (OPE) is widely applied in sectors such as pharmaceuticals and e-commerce to evaluate the efficacy of novel products or policies from offline datasets. This paper introduces a causal deepset framework that relaxes several key structural assumptions, primarily the mean-field assumption, prevalent in existing OPE methodologies that handle spatio-temporal interference. These traditional assumptions frequently prove inadequate in real-world settings, thereby restricting the capability of current OPE methods to effectively address complex interference effects. In response, we advocate for the implementation of the permutation invariance (PI) assumption. This innovative approach enables the data-driven, adaptive learning of the mean-field function, offering a more flexible estimation method beyond conventional averaging. Furthermore, we present novel algorithms that incorporate the PI assumption into OPE and thoroughly examine their theoretical foundations. Our numerical analyses demonstrate that this novel approach yields significantly more precise estimations than existing baseline algorithms, thereby substantially improving the practical applicability and effectiveness of OPE methodologies. A Python implementation of our proposed method is available at https://github.com/BIG-S2/Causal-Deepsets.

Transformer-based large language models have achieved remarkable performance across various natural language processing tasks. However, they often struggle with seemingly easy tasks like arithmetic despite their vast capabilities. This stark disparity raise human's concerns about their safe and ethical use, hinder their widespread adoption.In this paper, we focus on a typical arithmetic task, integer multiplication, to explore and explain the imperfection of transformers in this domain. We provide comprehensive analysis of a vanilla transformer trained to perform n-digit integer multiplication. Our observations indicate that the model decomposes multiplication task into multiple parallel subtasks, sequentially optimizing each subtask for each digit to complete the final multiplication. Based on observation and analysis, we infer the reasons of transformers deficiencies in multiplication tasks lies in their difficulty in calculating successive carryovers and caching intermediate results, and confirmed this inference through experiments. Guided by these findings, we propose improvements to enhance transformers performance on multiplication tasks. These enhancements are validated through rigorous testing and mathematical modeling, not only enhance transformer's interpretability, but also improve its performance, e.g., we achieve over 99.9% accuracy on 5-digit integer multiplication with a tiny transformer, outperform LLMs GPT-4. Our method contributes to the broader fields of model understanding and interpretability, paving the way for analyzing more complex tasks and Transformer models. This work underscores the importance of explainable AI, helping to build trust in large language models and promoting their adoption in critical applications., Comment: 8 pages, 5 figures

Human pose estimation remains a multifaceted challenge in computer vision, pivotal across diverse domains such as behavior recognition, human-computer interaction, and pedestrian tracking. This paper proposes an improved method based on the spatial-temporal graph convolution net-work (UGCN) to address the issue of missing human posture skeleton sequences in single-view videos. We present the improved UGCN, which allows the network to process 3D human pose data and improves the 3D human pose skeleton sequence, thereby resolving the occlusion issue., Comment: Proceedings of IEEE AICON2024

Large vision language models (LVLMs) often suffer from object hallucination, producing objects not present in the given images. While current benchmarks for object hallucination primarily concentrate on the presence of a single object class rather than individual entities, this work systematically investigates multi-object hallucination, examining how models misperceive (e.g., invent nonexistent objects or become distracted) when tasked with focusing on multiple objects simultaneously. We introduce Recognition-based Object Probing Evaluation (ROPE), an automated evaluation protocol that considers the distribution of object classes within a single image during testing and uses visual referring prompts to eliminate ambiguity. With comprehensive empirical studies and analysis of potential factors leading to multi-object hallucination, we found that (1). LVLMs suffer more hallucinations when focusing on multiple objects compared to a single object. (2). The tested object class distribution affects hallucination behaviors, indicating that LVLMs may follow shortcuts and spurious correlations. (3). Hallucinatory behaviors are influenced by data-specific factors, salience and frequency, and model intrinsic behaviors. We hope to enable LVLMs to recognize and reason about multiple objects that often occur in realistic visual scenes, provide insights, and quantify our progress towards mitigating the issues., Comment: Accepted to NeurIPS 2024 | Project page: https://multi-object-hallucination.github.io/

High-frequency primordial gravitational waves (PGWs) with wave numbers larger than the Hubble parameter at the end of inflation are originated from the ultraviolet (UV) modes, which are never stretched out of the horizon. Such a UV tail of the PGW energy spectrum has a spurious logarithmic divergence. We study the origin of such a divergence, and find that it comes from the instantaneous inflation-to-post-inflation transition, which can be removed by considering a finite duration. For the first time, we obtain a semi-analytical expression for the PGW energy spectrum. We find that the UV tail decays exponentially, while the decay rate depends solely on the transition rate. When there is a stiff post-inflationary stage, the enhanced PGW displays a characteristic spectral shape of power-law increasing and exponential decaying. We propose a fitting formula which can be used for signal searching., Comment: 23 pages, 13 figures

Most economic theories typically assume that financial market participants are fully rational individuals and use mathematical models to simulate human behavior in financial markets. However, human behavior is often not entirely rational and is challenging to predict accurately with mathematical models. In this paper, we propose \textbf{A}gent-based \textbf{S}imulated \textbf{F}inancial \textbf{M}arket (ASFM), which first constructs a simulated stock market with a real order matching system. Then, we propose a large language model based agent as the stock trader, which contains the profile, observation, and tool-learning based action module. The trading agent can comprehensively understand current market dynamics and financial policy information, and make decisions that align with their trading strategy. In the experiments, we first verify that the reactions of our ASFM are consistent with the real stock market in two controllable scenarios. In addition, we also conduct experiments in two popular economics research directions, and we find that conclusions drawn in our \model align with the preliminary findings in economics research. Based on these observations, we believe our proposed ASFM provides a new paradigm for economic research.

Single pulse all-optical switching of magnetization (AOS) in Co/Gd based synthetic ferrimagnets carries promises for hybrid spintronic-photonic integration. A crucial next step progressing towards this vision is to gain insight into AOS and multi-domain state (MDS) behavior using longer pulses, which is compatible with state-of-the-art integrated photonics. In this work, we present our studies on the AOS and MDS of [Co/Gd]n (n = 1, 2) using ps optical pulses across a large composition range. We theoretically and experimentally show that a large Gd layer thickness can enhance the AOS energy efficiency and maximum pulse duration. We have identified two augmenting roles of Gd in extending the maximum pulse duration. On the inter-atomic level, we found that more Gd offers a prolonged angular momentum supply to Co. On the micromagnetic level, a higher Gd content brings the system to be closer to magnetic compensation in the equilibrized hot state, thereby reducing the driving force for thermally assisted nucleation of domain walls, combating the formation of a MDS. Our study presents a composition overview of AOS in [Co/Gd]n and offers useful physical insights regarding AOS fundamentals as well as the projected photonic integration.

The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies. By leveraging the principles of physics to inform and enhance deep learning models, we can develop more robust and accurate vision systems. Physics-based vision aims to invert the processes to recover scene properties such as shape, reflectance, light distribution, and medium properties from images. In recent years, deep learning has shown promising improvements for various vision tasks, and when combined with physics-based vision, these approaches can enhance the robustness and accuracy of vision systems. This technical report summarizes the outcomes of the Physics-Based Vision Meets Deep Learning (PBDL) 2024 challenge, held in CVPR 2024 workshop. The challenge consisted of eight tracks, focusing on Low-Light Enhancement and Detection as well as High Dynamic Range (HDR) Imaging. This report details the objectives, methodologies, and results of each track, highlighting the top-performing solutions and their innovative approaches., Comment: CVPR 2024 PBDL Challenges: https://pbdl-ws.github.io/pbdl2024/challenge/index.html

Many tasks within NLP can be framed as sequential decision problems, ranging from sequence tagging to text generation. However, for many tasks, the standard training methods, including maximum likelihood (teacher forcing) and scheduled sampling, suffer from exposure bias and a mismatch between metrics employed during training and inference. DAgger provides a solution to mitigate these problems, yet it requires a metric-specific dynamic oracle algorithm, which does not exist for many common metrics like span-based F1, ROUGE, and BLEU. In this paper, we develop these novel dynamic oracles and show they maintain DAgger's no-regret guarantee for decomposable metrics like span-based F1. We evaluate the algorithm's performance on named entity recognition (NER), text summarization, and machine translation (MT). While DAgger with dynamic oracle yields less favorable results in our MT experiments, it outperforms the baseline techniques in NER and text summarization.

The compelling goal of eradicating undesirable data behaviors, while preserving usual model functioning, underscores the significance of machine unlearning within the domain of large language models (LLMs). Recent research has begun to approach LLM unlearning via gradient ascent (GA) -- increasing the prediction risk for those training strings targeted to be unlearned, thereby erasing their parameterized responses. Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning, resulting in various undesirable model behaviors, such as catastrophic forgetting, that diminish their practical utility. In this paper, we suggest a set of metrics that can capture multiple facets of real-world utility and propose several controlling methods that can regulate the extent of excessive unlearning. Accordingly, we suggest a general framework to better reflect the practical efficacy of various unlearning methods -- we begin by controlling the unlearning procedures/unlearned models such that no excessive unlearning occurs and follow by the evaluation for unlearning efficacy. Our experimental analysis on established benchmarks revealed that GA-based methods are far from perfect in practice, as strong unlearning is at the high cost of hindering the model utility. We conclude that there is still a long way towards practical and effective LLM unlearning, and more efforts are required in this field.

Computer Science (CS) stands as a testament to the intricacies of human intelligence, profoundly advancing the development of artificial intelligence and modern society. However, the current community of large language models (LLMs) overly focuses on benchmarks for analyzing specific foundational skills (e.g. mathematics and code generation), neglecting an all-round evaluation of the computer science field. To bridge this gap, we introduce CS-Bench, the first bilingual (Chinese-English) benchmark dedicated to evaluating the performance of LLMs in computer science. CS-Bench comprises approximately 5K meticulously curated test samples, covering 26 subfields across 4 key areas of computer science, encompassing various task forms and divisions of knowledge and reasoning. Utilizing CS-Bench, we conduct a comprehensive evaluation of over 30 mainstream LLMs, revealing the relationship between CS performance and model scales. We also quantitatively analyze the reasons for failures in existing LLMs and highlight directions for improvements, including knowledge supplementation and CS-specific reasoning. Further cross-capability experiments show a high correlation between LLMs' capabilities in computer science and their abilities in mathematics and coding. Moreover, expert LLMs specialized in mathematics and coding also demonstrate strong performances in several CS subfields. Looking ahead, we envision CS-Bench serving as a cornerstone for LLM applications in the CS field and paving new avenues in assessing LLMs' diverse reasoning capabilities. The CS-Bench data and evaluation code are available at https://github.com/csbench/csbench., Comment: Work in progress