Search

LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the network. To extend coding capabilities beyond function-level tasks to more challenging software-level development, we further propose rSDE-Bench, a requirement-oriented software development benchmark, which features complex and diverse software requirements along with automatic evaluation of requirement correctness. Our experiments show that: i) The automatic requirement-aware evaluation in rSDE-Bench closely aligns with human evaluations, validating its reliability as a software-level coding benchmark. ii) EvoMAC outperforms previous SOTA methods on both the software-level rSDE-Bench and the function-level HumanEval benchmarks, reflecting its superior coding capabilities. The benchmark can be downloaded at https://yuzhu-cai.github.io/rSDE-Bench/., Comment: 25 pages

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area., Comment: Project Page: https://github.com/SihengLi99/LLM-Honesty-Survey

Content-based histopathological image retrieval (CBHIR) has gained attention in recent years, offering the capability to return histopathology images that are content-wise similar to the query one from an established database. However, in clinical practice, the continuously expanding size of WSI databases limits the practical application of the current CBHIR methods. In this paper, we propose a Lifelong Whole Slide Retrieval (LWSR) framework to address the challenges of catastrophic forgetting by progressive model updating on continuously growing retrieval database. Our framework aims to achieve the balance between stability and plasticity during continuous learning. To preserve system plasticity, we utilize local memory bank with reservoir sampling method to save instances, which can comprehensively encompass the feature spaces of both old and new tasks. Furthermore, A distance consistency rehearsal (DCR) module is designed to ensure the retrieval queue's consistency for previous tasks, which is regarded as stability within a lifelong CBHIR system. We evaluated the proposed method on four public WSI datasets from TCGA projects. The experimental results have demonstrated the proposed method is effective and is superior to the state-of-the-art methods., Comment: Accepted for MICCAI 2024

Tool-augmented large language models (LLMs) are rapidly being integrated into real-world applications. Due to the lack of benchmarks, the community has yet to fully understand the hallucination issues within these models. To address this challenge, we introduce a comprehensive diagnostic benchmark, ToolBH. Specifically, we assess the LLM's hallucinations through two perspectives: depth and breadth. In terms of depth, we propose a multi-level diagnostic process, including (1) solvability detection, (2) solution planning, and (3) missing-tool analysis. For breadth, we consider three scenarios based on the characteristics of the toolset: missing necessary tools, potential tools, and limited functionality tools. Furthermore, we developed seven tasks and collected 700 evaluation samples through multiple rounds of manual annotation. The results show the significant challenges presented by the ToolBH benchmark. The current advanced models Gemini-1.5-Pro and GPT-4o only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100. In this benchmark, larger model parameters do not guarantee better performance; the training data and response strategies also play crucial roles in tool-enhanced LLM scenarios. Our diagnostic analysis indicates that the primary reason for model errors lies in assessing task solvability. Additionally, open-weight models suffer from performance drops with verbose replies, whereas proprietary models excel with longer reasoning.

Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in natural language processing. In particular, large language models (LLMs) can hardly produce written works at the level of human experts due to the extremely high complexity of literature writing. In this paper, we present HoLLMwood, an automated framework for unleashing the creativity of LLMs and exploring their potential in screenwriting, which is a highly demanding task. Mimicking the human creative process, we assign LLMs to different roles involved in the real-world scenario. In addition to the common practice of treating LLMs as ${Writer}$, we also apply LLMs as ${Editor}$, who is responsible for providing feedback and revision advice to ${Writer}$. Besides, to enrich the characters and deepen the plots, we introduce a role-playing mechanism and adopt LLMs as ${Actors}$ that can communicate and interact with each other. Evaluations on automatically generated screenplays show that HoLLMwood substantially outperforms strong baselines in terms of coherence, relevance, interestingness and overall quality.

We introduce a new benchmark, ChartMimic, aimed at assessing the visually-grounded code generation capabilities of large multimodal models (LMMs). ChartMimic utilizes information-intensive visual charts and textual instructions as inputs, requiring LMMs to generate the corresponding code for chart rendering. ChartMimic includes 1,000 human-curated (figure, instruction, code) triplets, which represent the authentic chart use cases found in scientific papers across various domains(e.g., Physics, Computer Science, Economics, etc). These charts span 18 regular types and 4 advanced types, diversifying into 191 subcategories. Furthermore, we propose multi-level evaluation metrics to provide an automatic and thorough assessment of the output code and the rendered charts. Unlike existing code generation benchmarks, ChartMimic places emphasis on evaluating LMMs' capacity to harmonize a blend of cognitive capabilities, encompassing visual understanding, code generation, and cross-modal reasoning. The evaluation of 3 proprietary models and 11 open-weight models highlights the substantial challenges posed by ChartMimic. Even the advanced GPT-4V, Claude-3-opus only achieve an average score of 73.2 and 53.7, respectively, indicating significant room for improvement. We anticipate that ChartMimic will inspire the development of LMMs, advancing the pursuit of artificial general intelligence., Comment: Data and code are available at https://github.com/ChartMimic/ChartMimic

Federated learning has enabled multiple parties to collaboratively train large language models without directly sharing their data (FedLLM). Following this training paradigm, the community has put massive efforts from diverse aspects including framework, performance, and privacy. However, an unpleasant fact is that there are currently no realistic datasets and benchmarks for FedLLM and previous works all rely on artificially constructed datasets, failing to capture properties in real-world scenarios. Addressing this, we propose FedLLM-Bench, which involves 8 training methods, 4 training datasets, and 6 evaluation metrics, to offer a comprehensive testbed for the FedLLM community. FedLLM-Bench encompasses three datasets (e.g., user-annotated multilingual dataset) for federated instruction tuning and one dataset (e.g., user-annotated preference dataset) for federated preference alignment, whose scale of client number ranges from 38 to 747. Our datasets incorporate several representative diversities: language, quality, quantity, instruction, length, embedding, and preference, capturing properties in real-world scenarios. Based on FedLLM-Bench, we conduct experiments on all datasets to benchmark existing FL methods and provide empirical insights (e.g., multilingual collaboration). We believe that our FedLLM-Bench can benefit the FedLLM community by reducing required efforts, providing a practical testbed, and promoting fair comparisons. Code and datasets are available at https://github.com/rui-ye/FedLLM-Bench., Comment: 22 pages

Reaching a high precision of the top quark mass is an important task of the Large Hadron Collider. We perform a feasibility study of measuring the top quark mass through the three-point energy correlator. The expected sensitivity of the top quark mass in the boosted regime is presented. We further introduce its application to the low top $p_\text{T}$ regime and demonstrate that both the W boson and the top quark masses could be extracted from this single observable. Compared to traditional observables, the energy correlator shows robustness to uncertainties that usually dominate experimental measurements and provides a promising way to improve experimental precision., Comment: 10 pages, 6 figures, matches published version

Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing mechanism. However, the unchosen experts in MoE models do not contribute to the output, potentially leading to underutilization of the model's capacity. In this work, we first conduct exploratory studies to demonstrate that increasing the number of activated experts does not necessarily improve and can even degrade the output quality. Then, we show that output distributions from an MoE model using different routing strategies substantially differ, indicating that different experts do not always act synergistically. Motivated by these findings, we propose Self-Contrast Mixture-of-Experts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. In SCMoE, the next-token probabilities are determined by contrasting the outputs from strong and weak activation using the same MoE model. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding. Experiments on several benchmarks (GSM8K, StrategyQA, MBPP and HumanEval) demonstrate that SCMoE can consistently enhance Mixtral 8x7B's reasoning capability across various domains. For example, it improves the accuracy on GSM8K from 61.79 to 66.94. Moreover, combining SCMoE with self-consistency yields additional gains, increasing major@20 accuracy from 75.59 to 78.31., Comment: NeurIPS 2024

Personalized fairness in recommendations has been attracting increasing attention from researchers. The existing works often treat a fairness requirement, represented as a collection of sensitive attributes, as a hyper-parameter, and pursue extreme fairness by completely removing information of sensitive attributes from the learned fair embedding, which suffer from two challenges: huge training cost incurred by the explosion of attribute combinations, and the suboptimal trade-off between fairness and accuracy. In this paper, we propose a novel Adaptive Fair Representation Learning (AFRL) model, which achieves a real personalized fairness due to its advantage of training only one model to adaptively serve different fairness requirements during inference phase. Particularly, AFRL treats fairness requirements as inputs and can learn an attribute-specific embedding for each attribute from the unfair user embedding, which endows AFRL with the adaptability during inference phase to determine the non-sensitive attributes under the guidance of the user's unique fairness requirement. To achieve a better trade-off between fairness and accuracy in recommendations, AFRL conducts a novel Information Alignment to exactly preserve discriminative information of non-sensitive attributes and incorporate a debiased collaborative embedding into the fair embedding to capture attribute-independent collaborative signals, without loss of fairness. Finally, the extensive experiments conducted on real datasets together with the sound theoretical analysis demonstrate the superiority of AFRL., Comment: This paper has been accepted by SIGIR '24

Federated learning (FL) enables leveraging distributed private data for model training in a privacy-preserving way. However, data heterogeneity significantly limits the performance of current FL methods. In this paper, we propose a novel FL framework termed FedGC, designed to mitigate data heterogeneity issues by diversifying private data with generative content. FedGC is a simple-to-implement framework as it only introduces a one-shot step of data generation. In data generation, we summarize three crucial and worth-exploring aspects (budget allocation, prompt design, and generation guidance) and propose three solution candidates for each aspect. Specifically, to achieve a better trade-off between data diversity and fidelity for generation guidance, we propose to generate data based on the guidance of prompts and real data simultaneously. The generated data is then merged with private data to facilitate local model training. Such generative data increases the diversity of private data to prevent each client from fitting the potentially biased private data, alleviating the issue of data heterogeneity. We conduct a systematic empirical study on FedGC, covering diverse baselines, datasets, scenarios, and modalities. Interesting findings include (1) FedGC consistently and significantly enhances the performance of FL methods, even when notable disparities exist between generative and private data; (2) FedGC achieves both better performance and privacy-preservation. We wish this work can inspire future works to further explore the potential of enhancing FL with generative content., Comment: 19 pages

Information-seeking conversation, which aims to help users gather information through conversation, has achieved great progress in recent years. However, the research is still stymied by the scarcity of training data. To alleviate this problem, we propose AutoConv for synthetic conversation generation, which takes advantage of the few-shot learning ability and generation capacity of large language models (LLM). Specifically, we formulate the conversation generation problem as a language modeling task, then finetune an LLM with a few human conversations to capture the characteristics of the information-seeking process and use it for generating synthetic conversations with high quality. Experimental results on two frequently-used datasets verify that AutoConv has substantial improvements over strong baselines and alleviates the dependence on human annotation. In addition, we also provide several analysis studies to promote future research., Comment: Accepted to ACL 2023 Main Conference (Short)

Question answering plays a pivotal role in human daily life because it involves our acquisition of knowledge about the world. However, due to the dynamic and ever-changing nature of real-world facts, the answer can be completely different when the time constraint in the question changes. Recently, Large Language Models (LLMs) have shown remarkable intelligence in question answering, while our experiments reveal that the aforementioned problems still pose a significant challenge to existing LLMs. This can be attributed to the LLMs' inability to perform rigorous reasoning based on surface-level text semantics. To overcome this limitation, rather than requiring LLMs to directly answer the question, we propose a novel approach where we reframe the $\textbf{Q}$uestion $\textbf{A}$nswering task $\textbf{a}$s $\textbf{P}$rogramming ($\textbf{QAaP}$). Concretely, by leveraging modern LLMs' superior capability in understanding both natural language and programming language, we endeavor to harness LLMs to represent diversely expressed text as well-structured code and select the best matching answer from multiple candidates through programming. We evaluate our QAaP framework on several time-sensitive question answering datasets and achieve decent improvement, up to $14.5$% over strong baselines. Our codes and data are available at https://github.com/TianHongZXY/qaap, Comment: Accepted to EMNLP 2023 Main Conference

Named-entity recognition (NER) detects texts with predefined semantic labels and is an essential building block for natural language processing (NLP). Notably, recent NER research focuses on utilizing massive extra data, including pre-training corpora and incorporating search engines. However, these methods suffer from high costs associated with data collection and pre-training, and additional training process of the retrieved data from search engines. To address the above challenges, we completely frame NER as a machine reading comprehension (MRC) problem, called NER-to-MRC, by leveraging MRC with its ability to exploit existing data efficiently. Several prior works have been dedicated to employing MRC-based solutions for tackling the NER problem, several challenges persist: i) the reliance on manually designed prompts; ii) the limited MRC approaches to data reconstruction, which fails to achieve performance on par with methods utilizing extensive additional data. Thus, our NER-to-MRC conversion consists of two components: i) transform the NER task into a form suitable for the model to solve with MRC in a efficient manner; ii) apply the MRC reasoning strategy to the model. We experiment on 6 benchmark datasets from three domains and achieve state-of-the-art performance without external data, up to 11.24% improvement on the WNUT-16 dataset.

The performance of nanoscale electronic devices based on a two-three dimensional (2D-3D) interface is significantly affected by the electrical contacts that interconnect these materials with external circuitry. This work investigates charge transport effects at the 2D-3D ohmic contact coupled with the thermionic injection model for graphene/Si Schottky junction. Here, w e focus on the intrinsic properties of graphene-metal contacts, paying particular attention to the nature of the contact failure mechanism under high electrical stress. According to our findings, severe current crowding (CC) effects in highly conductive electrical contact significantly affect device failure that can be reduced by spatially varying the contact properties and geometry. The impact of electrical breakdown on material degradation is systematically analyzed by atomic force, Raman, scanning electron, and energy dispersive X-ray spectroscopies. Our devices withstand high electrostatic discharge spikes over a longer period, manifesting high robustness and operational stability. This research paves the way towards a highly robust and reliable graphene/Si heterostructure in futuristic on-chip integration in dynamic switching. The methods we employed here can be extended for other nanoscale electronic devices based on 2D-3D interfaces

Large-scale pre-trained language models (PLMs) bring new opportunities to challenging problems, especially those that need high-level intelligence, such as the math word problem (MWPs). However, directly applying existing PLMs to MWPs can fail as the generation process lacks sufficient supervision and thus lacks fast adaptivity as humans. We notice that human reasoning has a dual reasoning framework that consists of an immediate reaction system (system 1) and a delicate reasoning system (system 2), where the entire reasoning is determined by their interaction. This inspires us to develop a cooperative reasoning-induced PLM for solving MWPs, called Cooperative Reasoning (CoRe), resulting in a human-like reasoning architecture with system 1 as the generator and system 2 as the verifier. In our approach, the generator is responsible for generating reasoning paths, and the verifiers are used to supervise the evaluation in order to obtain reliable feedback for the generator. We evaluate our CoRe framework on several mathematical reasoning datasets and achieve decent improvement over state-of-the-art methods, up to 9.6% increase over best baselines. Our codes are available at https://github.com/TianHongZXY/CoRe, Comment: Accepted to ACL 2023 Main Conference; Camera Ready

We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and sentiment analysis. Zero-shot learning aims to train a model on a given task such that it can address new learning tasks without any additional training. Our approach converts zero-shot learning into multiple-choice tasks, avoiding problems in commonly used large-scale generative models such as FLAN. It not only adds generalization ability to models but also significantly reduces the number of parameters. Our method shares the merits of efficient training and deployment. Our approach shows state-of-the-art performance on several benchmarks and produces satisfactory results on tasks such as natural language inference and text classification. Our model achieves this success with only 235M parameters, which is substantially smaller than state-of-the-art models with billions of parameters. The code and pre-trained models are available at https://github.com/IDEA-CCNL/Fengshenbang-LM ., Comment: EMNLP 2022

Nowadays, foundation models become one of fundamental infrastructures in artificial intelligence, paving ways to the general intelligence. However, the reality presents two urgent challenges: existing foundation models are dominated by the English-language community; users are often given limited resources and thus cannot always use foundation models. To support the development of the Chinese-language community, we introduce an open-source project, called Fengshenbang, which leads by the research center for Cognitive Computing and Natural Language (CCNL). Our project has comprehensive capabilities, including large pre-trained models, user-friendly APIs, benchmarks, datasets, and others. We wrap all these in three sub-projects: the Fengshenbang Model, the Fengshen Framework, and the Fengshen Benchmark. An open-source roadmap, Fengshenbang, aims to re-evaluate the open-source community of Chinese pre-trained large-scale models, prompting the development of the entire Chinese large-scale model community. We also want to build a user-centered open-source ecosystem to allow individuals to access the desired models to match their computing resources. Furthermore, we invite companies, colleges, and research institutions to collaborate with us to build the large-scale open-source model-based ecosystem. We hope that this project will be the foundation of Chinese cognitive intelligence., Comment: Added the Chinese version and is now a bilingual paper

Concomitant administration of drugs can cause drug-drug interactions (DDIs). Some drug combinations are beneficial, but other ones may cause negative effects which are previously unrecorded. Previous works on DDI prediction usually rely on hand-engineered domain knowledge, which is laborious to obtain. In this work, we propose a novel model, Molecular Substructure-Aware Network (MSAN), to effectively predict potential DDIs from molecular structures of drug pairs. We adopt a Transformer-like substructure extraction module to acquire a fixed number of representative vectors that are associated with various substructure patterns of the drug molecule. Then, interaction strength between the two drugs' substructures will be captured by a similarity-based interaction module. We also perform a substructure dropping augmentation before graph encoding to alleviate overfitting. Experimental results from a real-world dataset reveal that our proposed model achieves the state-of-the-art performance. We also show that the predictions of our model are highly interpretable through a case study., Comment: Accepted to CIKM 2022 (Short), camera ready version