Search

While large language models (LLMs) have demonstrated remarkable abilities across various fields, hallucination remains a significant challenge. Recent studies have explored hallucinations through the lens of internal representations, proposing mechanisms to decipher LLMs' adherence to facts. However, these approaches often fail to generalize to out-of-distribution data, leading to concerns about whether internal representation patterns reflect fundamental factual awareness, or only overfit spurious correlations on the specific datasets. In this work, we investigate whether a universal truthfulness hyperplane that distinguishes the model's factually correct and incorrect outputs exists within the model. To this end, we scale up the number of training datasets and conduct an extensive evaluation -- we train the truthfulness hyperplane on a diverse collection of over 40 datasets and examine its cross-task, cross-domain, and in-domain generalization. Our results indicate that increasing the diversity of the training datasets significantly enhances the performance in all scenarios, while the volume of data samples plays a less critical role. This finding supports the optimistic hypothesis that a universal truthfulness hyperplane may indeed exist within the model, offering promising directions for future research.

Human priors play a crucial role in efficiently utilizing data in deep learning. However, with the development of large language models (LLMs), there is an increasing emphasis on scaling both model size and data volume, which often diminishes the importance of human priors in data construction. Influenced by these trends, existing Small Language Models (SLMs) mainly rely on web-scraped large-scale training data, neglecting the proper incorporation of human priors. This oversight limits the training efficiency of language models in resource-constrained settings. In this paper, we propose a principle to leverage human priors for data construction. This principle emphasizes achieving high-performance SLMs by training on a concise dataset that accommodates both semantic diversity and data quality consistency, while avoiding benchmark data leakage. Following this principle, we train an SLM named HARE-1.1B. Extensive experiments on large-scale benchmark datasets demonstrate that HARE-1.1B performs favorably against state-of-the-art SLMs, validating the effectiveness of the proposed principle. Additionally, this provides new insights into efficient language model training in resource-constrained environments from the view of human priors.

Large language models (LLMs) frequently hallucinate and produce factual errors, yet our understanding of why they make these errors remains limited. In this study, we delve into the underlying mechanisms of LLM hallucinations from the perspective of inner representations, and discover a salient pattern associated with hallucinations: correct generations tend to have sharper context activations in the hidden states of the in-context tokens, compared to the incorrect ones. Leveraging this insight, we propose an entropy-based metric to quantify the ``sharpness'' among the in-context hidden states and incorporate it into the decoding process to formulate a constrained decoding approach. Experiments on various knowledge-seeking and hallucination benchmarks demonstrate our approach's consistent effectiveness, for example, achieving up to an 8.6 point improvement on TruthfulQA. We believe this study can improve our understanding of hallucinations and serve as a practical solution for hallucination mitigation., Comment: code repo is available at: https://github.com/hkust-nlp/Activation_decoding.git

Assessing factuality of text generated by large language models (LLMs) is an emerging yet crucial research area, aimed at alerting users to potential errors and guiding the development of more reliable LLMs. Nonetheless, the evaluators assessing factuality necessitate suitable evaluation themselves to gauge progress and foster advancements. This direction remains under-explored, resulting in substantial impediments to the progress of factuality evaluators. To mitigate this issue, we introduce a benchmark for Factuality Evaluation of large Language Models, referred to as felm. In this benchmark, we collect responses generated from LLMs and annotate factuality labels in a fine-grained manner. Contrary to previous studies that primarily concentrate on the factuality of world knowledge (e.g.~information from Wikipedia), felm focuses on factuality across diverse domains, spanning from world knowledge to math and reasoning. Our annotation is based on text segments, which can help pinpoint specific factual errors. The factuality annotations are further supplemented by predefined error types and reference links that either support or contradict the statement. In our experiments, we investigate the performance of several LLM-based factuality evaluators on felm, including both vanilla LLMs and those augmented with retrieval mechanisms and chain-of-thought processes. Our findings reveal that while retrieval aids factuality evaluation, current LLMs are far from satisfactory to faithfully detect factual errors., Comment: Accepted by NeurIPS 2023 Track on Datasets and Benchmarks

The joint design of the optical system and the downstream algorithm is a challenging and promising task. Due to the demand for balancing the global optimal of imaging systems and the computational cost of physical simulation, existing methods cannot achieve efficient joint design of complex systems such as smartphones and drones. In this work, starting from the perspective of the optical design, we characterize the optics with separated aberrations. Additionally, to bridge the hardware and software without gradients, an image simulation system is presented to reproduce the genuine imaging procedure of lenses with large field-of-views. As for aberration correction, we propose a network to perceive and correct the spatially varying aberrations and validate its superiority over state-of-the-art methods. Comprehensive experiments reveal that the preference for correcting separated aberrations in joint design is as follows: longitudinal chromatic aberration, lateral chromatic aberration, spherical aberration, field curvature, and coma, with astigmatism coming last. Drawing from the preference, a 10% reduction in the total track length of the consumer-level mobile phone lens module is accomplished. Moreover, this procedure spares more space for manufacturing deviations, realizing extreme-quality enhancement of computational photography. The optimization paradigm provides innovative insight into the practical joint design of sophisticated optical systems and post-processing algorithms., Comment: 19 pages

The emergence of generative pre-trained models has facilitated the synthesis of high-quality text, but it has also posed challenges in identifying factual errors in the generated text. In particular: (1) A wider range of tasks now face an increasing risk of containing factual errors when handled by generative models. (2) Generated texts tend to be lengthy and lack a clearly defined granularity for individual facts. (3) There is a scarcity of explicit evidence available during the process of fact checking. With the above challenges in mind, in this paper, we propose FacTool, a task and domain agnostic framework for detecting factual errors of texts generated by large language models (e.g., ChatGPT). Experiments on four different tasks (knowledge-based QA, code generation, mathematical reasoning, and scientific literature review) show the efficacy of the proposed method. We release the code of FacTool associated with ChatGPT plugin interface at https://github.com/GAIR-NLP/factool .

Photographing in the under-illuminated scenes, the presence of complex light sources often leave strong flare artifacts in images, where the intensity, the spectrum, the reflection, and the aberration altogether contribute the deterioration. Besides the image quality, it also influence the performance of down-stream visual applications. Thus, removing the lens flare and ghosts is a challenge issue especially in low-light environment. However, existing methods for flare removal mainly restricted to the problems of inadequate simulation and real-world capture, where the categories of scattered flares are singular and the reflected ghosts are unavailable. Therefore, a comprehensive deterioration procedure is crucial for constructing the dataset of flare removal. Based on the theoretical analysis and real-world evaluation, we propose a well-developed methodology for generating the data-pairs with flare deterioration. The procedure is comprehensive, where the similarity of scattered flares and the symmetric effect of reflected ghosts are realized. Moreover, we also construct a real-shot pipeline that respectively processes the effects of scattering and reflective flares, aiming to directly generate the data for end-to-end methods. Experimental results show that the proposed methodology add diversity to the existing flare datasets and construct a comprehensive mapping procedure for flare data pairs. And our method facilities the data-driven model to realize better restoration in flare images and proposes a better evaluation system based on real shots, resulting promote progress in the area of real flare removal.

The large language model and high-level vision model have achieved impressive performance improvements with large datasets and model sizes. However, low-level computer vision tasks, such as image dehaze and blur removal, still rely on a small number of datasets and small-sized models, which generally leads to overfitting and local optima. Therefore, we propose a framework to integrate large-model prior into low-level computer vision tasks. Just as with the task of image segmentation, the degradation of haze is also texture-related. So we propose to detect gray-scale coding, network channel expansion, and pre-dehaze structures to integrate large-model prior knowledge into any low-level dehazing network. We demonstrate the effectiveness and applicability of large models in guiding low-level visual tasks through different datasets and algorithms comparison experiments. Finally, we demonstrate the effect of grayscale coding, network channel expansion, and recurrent network structures through ablation experiments. Under the conditions where additional data and training resources are not required, we successfully prove that the integration of large-model prior knowledge will improve the dehaze performance and save training time for low-level visual tasks.

As an efficient alternative to conventional full finetuning, parameter-efficient finetuning (PEFT) is becoming the prevailing method to adapt pretrained language models. In PEFT, a lightweight module is learned on each dataset while the underlying pretrained language model remains unchanged, resulting in multiple compact modules representing diverse skills when applied to various domains and tasks. In this paper, we propose to compose these parameter-efficient modules through linear arithmetic operations in the weight space, thereby integrating different module capabilities. Specifically, we first define addition and negation operators for the module, and then further compose these two basic operators to perform flexible arithmetic. Our approach requires \emph{no additional training} and enables highly flexible module composition. We apply different arithmetic operations to compose the parameter-efficient modules for (1) distribution generalization, (2) multi-tasking, (3) unlearning, and (4) domain transfer. Additionally, we extend our approach to detoxify Alpaca-LoRA, the latest instruction-tuned large language model based on LLaMA. Empirical results demonstrate that our approach produces new and effective parameter-efficient modules that significantly outperform existing ones across all settings., Comment: NeurIPS 2023. Code is available at https://github.com/SJTU-LIT/PEM_composition

Detecting factual errors in summaries has been an important and challenging subject in summarization research. Inspired by the emergent ability of large language models (LLMs), we explore evaluating factual consistency of summaries by directly prompting LLMs. We present a comprehensive empirical study to assess the ability of LLMs as factual consistency evaluators, which consists of (1) analyzing different LLMs such as the GPT model series and Flan-T5; (2) investigating a variety of prompting methods including vanilla prompting, chain-of-thought prompting, and a sentence-by-sentence prompting method to tackle long summaries; and (3) evaluating on diverse summaries generated by multiple summarization systems, ranging from pre-transformer methods to SOTA pretrained models. Our experiments demonstrate that prompting LLMs is able to outperform the previous best factuality systems in all settings, by up to 12.2 absolute points in terms of the binary classification accuracy on inconsistency detection.

In digital images, the performance of optical aberration is a multivariate degradation, where the spectral of the scene, the lens imperfections, and the field of view together contribute to the results. Besides eliminating it at the hardware level, the post-processing system, which utilizes various prior information, is significant for correction. However, due to the content differences among priors, the pipeline that aligns these factors shows limited efficiency and unoptimized restoration. Here, we propose a prior quantization model to correct the optical aberrations in image processing systems. To integrate these messages, we encode various priors into a latent space and quantify them by the learnable codebooks. After quantization, the prior codes are fused with the image restoration branch to realize targeted optical aberration correction. Comprehensive experiments demonstrate the flexibility of the proposed method and validate its potential to accomplish targeted restoration for a specific camera. Furthermore, our model promises to analyze the correlation between the various priors and the optical aberration of devices, which is helpful for joint soft-hardware design., Comment: Submitted to Elsevier PRL. 5 pages, 5figures

Correcting the optical aberrations and the manufacturing deviations of cameras is a challenging task. Due to the limitation on volume and the demand for mass production, existing mobile terminals cannot rectify optical degradation. In this work, we systematically construct the perturbed lens system model to illustrate the relationship between the deviated system parameters and the spatial frequency response measured from photographs. To further address this issue, an optimization framework is proposed based on this model to build proxy cameras from the machining samples' SFRs. Engaging with the proxy cameras, we synthetic data pairs, which encode the optical aberrations and the random manufacturing biases, for training the learning-based algorithms. In correcting aberration, although promising results have been shown recently with convolutional neural networks, they are hard to generalize to stochastic machining biases. Therefore, we propose a dilated Omni-dimensional dynamic convolution and implement it in post-processing to account for the manufacturing degradation. Extensive experiments which evaluate multiple samples of two representative devices demonstrate that the proposed optimization framework accurately constructs the proxy camera. And the dynamic processing model is well-adapted to manufacturing deviations of different cameras, realizing perfect computational photography. The evaluation shows that the proposed method bridges the gap between optical design, system machining, and post-processing pipeline, shedding light on the joint of image signal reception (lens and sensor) and image signal processing., Comment: Published in IEEE TPAMI, 15 pages, 13 figures

As the popularity of mobile photography continues to grow, considerable effort is being invested in the reconstruction of degraded images. Due to the spatial variation in optical aberrations, which cannot be avoided during the lens design process, recent commercial cameras have shifted some of these correction tasks from optical design to postprocessing systems. However, without engaging with the optical parameters, these systems only achieve limited correction for aberrations.In this work, we propose a practical method for recovering the degradation caused by optical aberrations. Specifically, we establish an imaging simulation system based on our proposed optical point spread function model. Given the optical parameters of the camera, it generates the imaging results of these specific devices. To perform the restoration, we design a spatial-adaptive network model on synthetic data pairs generated by the imaging simulation system, eliminating the overhead of capturing training data by a large amount of shooting and registration. Moreover, we comprehensively evaluate the proposed method in simulations and experimentally with a customized digital-single-lens-reflex (DSLR) camera lens and HUAWEI HONOR 20, respectively. The experiments demonstrate that our solution successfully removes spatially variant blur and color dispersion. When compared with the state-of-the-art deblur methods, the proposed approach achieves better results with a lower computational overhead. Moreover, the reconstruction technique does not introduce artificial texture and is convenient to transfer to current commercial cameras. Project Page: \url{https://github.com/TanGeeGo/ImagingSimulation}., Comment: Published in ACM TOG. 15 pages, 13 figures

We present an image dehazing algorithm with high quality, wide application, and no data training or prior needed. We analyze the defects of the original dehazing model, and propose a new and reliable dehazing reconstruction and dehazing model based on the combination of optical scattering model and computer graphics lighting rendering model. Based on the new haze model and the images obtained by the cameras, we can reconstruct the three-dimensional space, accurately calculate the objects and haze in the space, and use the transparency relationship of haze to perform accurate haze removal. To obtain a 3D simulation dataset we used the Unreal 5 computer graphics rendering engine. In order to obtain real shot data in different scenes, we used fog generators, array cameras, mobile phones, underwater cameras and drones to obtain haze data. We use formula derivation, simulation data set and real shot data set result experimental results to prove the feasibility of the new method. Compared with various other methods, we are far ahead in terms of calculation indicators (4 dB higher quality average scene), color remains more natural, and the algorithm is more robust in different scenarios and best in the subjective perception., Comment: 12pages, 8figures

Primordial black holes (PBHs) may form from the collapse of matter overdensities shortly after the Big Bang. One may identify their existence by observing gravitational wave (GW) emissions from merging PBH binaries at high redshifts $z\gtrsim 30$, where astrophysical binary black holes (BBHs) are unlikely to merge. The next-generation ground-based GW detectors, Cosmic Explorer and Einstein Telescope, will be able to observe BBHs with total masses of $\mathcal{O}(10-100)~M_{\odot}$ at such redshifts. This paper serves as a companion paper of arXiv:2108.07276, focusing on the effect of higher-order modes (HoMs) in the waveform modeling, which may be detectable for these high redshift BBHs, on the estimation of source parameters. We perform Bayesian parameter estimation to obtain the measurement uncertainties with and without HoM modeling in the waveform for sources with different total masses, mass ratios, orbital inclinations and redshifts observed by a network of next-generation GW detectors. We show that including HoMs in the waveform model reduces the uncertainties of redshifts and masses by up to a factor of two, depending on the exact source parameters. We then discuss the implications for identifying PBHs with the improved single-event measurements, and expand the investigation of the model dependence of the relative abundance between the BBH mergers originating from the first stars and the primordial BBH mergers as shown in arXiv:2108.07276., Comment: 11 pages, 11 figures

The existence of primordial black holes (PBHs), which may form from the collapse of matter overdensities shortly after the Big Bang, is still under debate. Among the potential signatures of PBHs are gravitational waves (GWs) emitted from binary black hole (BBH) mergers at redshifts $z\gtrsim 30$, where the formation of astrophysical black holes is unlikely. Future ground-based GW detectors, Cosmic Explorer and Einstein Telescope, will be able to observe equal-mass BBH mergers with total mass of $\mathcal{O}(10-100)~M_{\odot}$ at such distances. In this work, we investigate whether the redshift measurement of a single BBH source can be precise enough to establish its primordial origin. We simulate BBHs of different masses, mass ratios and orbital orientations. We show that for BBHs with total masses between $20~M_{\odot}$ and $40~M_{\odot}$ merging at $z \geq 40$ one can infer $z>30$ at up to 97\% credibility, with a network of one Einstein Telescope, one 40-km Cosmic Explorer in the US and one 20-km Cosmic Explorer in Australia. A smaller network made of one Einstein Telescope and one 40-km Cosmic Explorer in the US measures $z>30$ at larger than 90\% credibility for roughly half of the sources than the larger network. We then assess the dependence of this result on the Bayesian redshift priors used for the analysis, specifically on the relative abundance of the BBH mergers originated from the first stars, and the primordial BBH mergers., Comment: 4.5 pages, 3 figures, 2 tables. Supplementary materials with 1 figure and 1 table. Submitted to PRL

Meta Reinforcement Learning (MRL) enables an agent to learn from a limited number of past trajectories and extrapolate to a new task. In this paper, we attempt to improve the robustness of MRL. We build upon model-agnostic meta-learning (MAML) and propose a novel method to generate adversarial samples for MRL by using Generative Adversarial Network (GAN). That allows us to enhance the robustness of MRL to adversal attacks by leveraging these attacks during meta training process.