论文检索

Guanting Dong, Jiajie Jin, Xiaoxi Li, Yutao Zhu, Zhicheng Dou, Ji-Rong Wen

Retrieval-augmented generation (RAG) has emerged as a pivotal technology in natural language processing, owing to its efficacy in generating factual content. However, its informative inputs and complex paradigms often lead to a greater variety of errors. Consequently, achieving automated on-policy assessment and error-oriented correction remain unresolved issues. In this paper, we propose RAG-Critic, a novel framework that leverages a critic-guided agentic workflow to improve RAG capabilities autonomously. Specifically, we initially design a data-driven error mining pipeline to establish a hierarchical RAG error system. Based on this system, we progressively align an error-critic model using a coarse-to-fine training objective, which automatically provides fine-grained error feedback. Finally, we design a critic-guided agentic RAG workflow that customizes executor-based solution flows based on the error-critic model’s feedback, facilitating an error-driven self-correction process. Experimental results across seven RAG-related datasets confirm the effectiveness of RAG-Critic, while qualitative analysis offers practical insights for achieving reliable RAG systems. Our dataset and code are available at https://github.com/RUC-NLPIR/RAG-Critic.

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Shaokai Chen, Mengshu Sun, Binbin Hu, Zhiqiang Zhang, Lei Liang, Wen Zhang 等

Large language models (LLMs) have demonstrated exceptional performance in text generation within current NLP research. However, the lack of factual accuracy is still a dark cloud hanging over the LLM skyscraper. Structural knowledge prompting (SKP) is a prominent paradigm to integrate external knowledge into LLMs by incorporating structural representations, achieving state-of-the-art results in many knowledge-intensive tasks. However, existing methods often focus on specific problems, lacking a comprehensive exploration of the generalization and capability boundaries of SKP. This paper aims to evaluate and rethink the generalization capability of the SKP paradigm from four perspectives including Granularity, Transferability, Scalability, and Universality. To provide a thorough evaluation, we introduce a novel multi-granular, multi-level benchmark called SUBARU, consisting of 9 different tasks with varying levels of granularity and difficulty. Through extensive experiments, we draw key conclusions regarding the generalization of SKP, offering insights to guide the future development and extension of the SKP paradigm.

Md Nayem Uddin, Amir Saeidi, Divij Handa, Agastya Seth, Tran Cao Son, Eduardo Blanco, Steven Corman, Chitta Baral

This paper introduces UnSeenTimeQA, a novel data contamination-free time-sensitive question-answering (TSQA) benchmark. It differs from existing TSQA benchmarks by avoiding web-searchable queries grounded in the real world. We present a series of time-sensitive event scenarios based on synthetically generated facts. It requires large language models (LLMs) to engage in genuine temporal reasoning without depending on the factual knowledge acquired during the pre-training phase. Our data generation framework enables on-demand generation of new samples, mitigating the risk of data leakage. We designed three types of time-sensitive questions to test LLMs’ temporal reasoning abilities over sequential and parallel event occurrences. Our evaluation of five LLMs on synthetic fact-based TSQA reveals mixed results: while they perform well on simpler subsets, their overall performance remains inferior as compared to real world fact-based TSQA. Error analysis indicates that LLMs face difficulties in reasoning over long-range event dependencies and parallel events.

Sanxing Chen, Yukun Huang, Bhuwan Dhingra

We show that existing evaluations for assessing the factuality of news from conventional sources, such as claims on fact-checking websites, result in high accuracies over time for LLM-based detectors—even after their knowledge cutoffs. This suggests that recent popular false information from such sources can be easily identified due to its likely presence in pre-training/retrieval corpora or the emergence of salient, yet shallow, patterns in these datasets. Instead, we argue that a proper factuality evaluation dataset should test a model’s ability to reason about current events by retrieving and reading related evidence. To this end, we develop a novel pipeline that leverages natural language feedback from a RAG-based detector to iteratively modify real-time news into deceptive variants that challenge LLMs. Our iterative rewrite decreases the binary classification ROC-AUC by an absolute 17.5 percent for a strong RAG-based GPT-4o detector. Our experiments reveal the important role of RAG in both evaluating and generating challenging news examples, as retrieval-free LLM detectors are vulnerable to unseen events and adversarial attacks, while feedback from RAG-based evaluation helps discover more deceitful patterns.

ZhaoDan Zhang, Zhao Zhang, Jin Zhang, Hui Xu, Xueqi Cheng

Stance detection is a pivotal task in Natural Language Processing (NLP), identifying textual attitudes toward various targets. Despite advances in using Large Language Models (LLMs), challenges persist due to hallucination-models generating plausible yet inaccurate content. Addressing these challenges, we introduce MPVStance, a framework that incorporates Multi-Perspective Verification (MPV) with Retrieval-Augmented Generation (RAG) across a structured five-step verification process. Our method enhances stance detection by rigorously validating each response from factual accuracy, logical consistency, contextual relevance, and other perspectives. Extensive testing on the SemEval-2016 and VAST datasets, including scenarios that challenge existing methods and comprehensive ablation studies, demonstrates that MPVStance significantly outperforms current models. It effectively mitigates hallucination issues and sets new benchmarks for reliability and accuracy in stance detection, particularly in zero-shot, few-shot, and challenging scenarios.

Hongzhan Lin, Yang Deng, Yuxuan Gu, Wenxuan Zhang, Jing Ma, See-Kiong Ng, Tat-Seng Chua

Large Language Models (LLMs) have significantly advanced the fact-checking studies. However, existing automated fact-checking evaluation methods rely on static datasets and classification metrics, which fail to automatically evaluate the justification production and uncover the nuanced limitations of LLMs in fact-checking. In this work, we introduce FACT-AUDIT, an agent-driven framework that adaptively and dynamically assesses LLMs’ fact-checking capabilities. Leveraging importance sampling principles and multi-agent collaboration, FACT-AUDIT generates adaptive and scalable datasets, performs iterative model-centric evaluations, and updates assessments based on model-specific responses. By incorporating justification production alongside verdict prediction, this framework provides a comprehensive and evolving audit of LLMs’ factual reasoning capabilities, to investigate their trustworthiness. Extensive experiments demonstrate that FACT-AUDIT effectively differentiates among state-of-the-art LLMs, providing valuable insights into model strengths and limitations in model-centric fact-checking analysis.

Applications · Language, Speech and Dialog

Anne Wu, Laurent Mazaré, Neil Zeghidour, Alexandre Défossez

We propose a novel preference alignment framework for improving spoken dialogue models on real-time conversations from user interactions. Current preference learning methods primarily focus on text-based language models, and are not directly suited to the complexities of real-time speech interactions, with richer dynamics (e.g. interruption, interjection) and no explicit segmentation between speaker turns.We create a large-scale dataset of more than 150,000 preference pairs from raw multi-turn speech conversations, annotated with AI feedback, to cover preferences over both linguistic content and temporal context variations. We leverage offline alignment methods to finetune a full-duplex autoregressive speech-to-speech model. Extensive experiments demonstrate that feedback on generic conversations can be consistently effective in improving spoken dialogue models to produce more factual, safer and more contextually aligned interactions. We deploy the finetuned model and conduct holistic human evaluations to assess the impact beyond single-turn conversations. Our findings shed light on the importance of a well-calibrated balance among various dynamics, crucial for natural real-time speech dialogue systems.

General Machine Learning · Causality

Jiaxuan Zhang, Emadeldeen Eldele, Fuyuan CAO, Yang Wang, Xiaoli Li, Jiye Liang

Estimating Individual Treatment Effects (ITE) from observational data is challenging due to covariate shift and counterfactual absence. While existing methods attempt to balance distributions globally, they often lack fine-grained sample-level alignment, especially in scenarios with significant individual heterogeneity. To address these issues, we reconsider counterfactual as a proxy to emulate balanced randomization. Furthermore, we derive a theoretical bound that links the expected ITE estimation error to both factual prediction errors and representation distances between factuals and counterfactuals. Building on this theoretical foundation, we propose FCCL, a novel method designed to effectively capture the nuances of potential outcomes under different treatments by (i) generating diffeomorphic counterfactuals that adhere to the data manifold while maintaining high semantic similarity to their factual counterparts, and (ii) mitigating distribution shift via sample-level alignment grounded in our derived generalization-error bound, which considers factual-counterfactual similarity and category consistency. Extensive evaluations on benchmark datasets demonstrate that FCCL outperforms 13 state-of-the-art methods, particularly in capturing individual-level heterogeneity and handling sparse boundary samples.

Theory · Deep Learning

Dake Bu, Wei Huang, Andi Han, Atsushi Nitanda, Qingfu Zhang, Hau-San Wong, Taiji Suzuki

In-context learning (ICL) has garnered significant attention for its ability to grasp functions/tasks from demonstrations. Recent studies suggest the presence of a latent **task/function vector** in LLMs during ICL. Merullo et al. (2024) showed that LLMs leverage this vector alongside the residual stream for Word2Vec-like vector arithmetic, solving factual-recall ICL tasks. Additionally, recent work empirically highlighted the key role of Question-Answer data in enhancing factual-recall capabilities. Despite these insights, a theoretical explanation remains elusive. To move one step forward, we propose a theoretical framework building on empirically grounded *hierarchical* concept modeling. We develop an optimization theory, showing how nonlinear residual transformers trained via gradient descent on cross-entropy loss perform factual-recall ICL tasks via vector arithmetic. We prove 0-1 loss convergence and show the strong generalization, including robustness to concept recombination and distribution shifts. These results elucidate the advantages of transformers over static embedding predecessors. Empirical simulations corroborate our theoretical insights.

Applications · Chemistry, Physics, and Earth Sciences

Zhang Jiasheng, Delvin Zhang, Shuang Liang, Zhengpin Li, ZHITAO YING, Jie Shao

Protein language models often struggle to capture biological functions due to their lack of factual knowledge (e.g., gene descriptions). Existing solutions leverage protein knowledge graphs (PKGs) as auxiliary pre-training objectives, but lack explicit integration of task-oriented knowledge, making them suffer from limited knowledge exploitation and catastrophic forgetting. The root cause is that they fail to align PKGs with task-specific data, forcing their knowledge modeling to adapt to the knowledge-isolated nature of downstream tasks. In this paper, we propose Knowledge-aware retrieval augmented protein language model (Kara), achieving the first task-oriented and explicit integration of PKGs and protein language models. With a knowledge retriever learning to predict linkages between PKG and task proteins, Kara unifies the knowledge integration of the pre-training and fine-tuning stages with a structure-based regularization, mitigating catastrophic forgetting. To ensure task-oriented integration, Kara uses contextualized virtual tokens to extract graph context as task-specific knowledge for new proteins. Experiments show that Kara outperforms existing knowledge-enhanced models in 6 representative tasks, achieving on average 5.1% improvements.

Deep Learning · Graph Neural Networks

Gregoire Fournier, Sourav Medya

Graph neural networks (GNNs) have been widely used in various domains such as social networks, molecular biology, or recommendation systems. Concurrently, different explanations methods of GNNs have arisen to complement its blackbox nature. Explanations of the GNNs’ predictions can be categorized into two types—factual and counterfactual. Given a GNN trained on binary classification into “accept” and “reject” classes, a global counterfactual explanation consists in generating a small set of “accept” graphs relevant to all of the input “reject” graphs. The transformation of a “reject” graph into an “accept” graph is called a recourse. A common recourse explanation is a small set of recourse, from which every “reject” graph can be turned into an “accept” graph. Although local counterfactual explanations have been studied extensively, the problem of finding common recourse for global counterfactual explanation remains unexplored, particularly for GNNs. In this paper, we formalize the common recourse explanation problem, and design an effective algorithm, COMRECGC, to solve it. We benchmark our algorithm against strong baselines on four different real-world graphs datasets and demonstrate the superior performance of COMRECGC against the competitors. We also compare the common recourse explanations to the graph counterfactual explanation, showing that common recourse explanations are either comparable or superior, making them worth considering for applications such as drug discovery or computational biology.

General Machine Learning · Causality

Hechuan Wen, Tong Chen, Mingming Gong, Li Kheng Chai, Shazia Sadiq, Hongzhi Yin

Although numerous complex algorithms for treatment effect estimation have been developed in recent years, their effectiveness remains limited when handling insufficiently labeled training sets due to the high cost of labeling the post-treatment effect, e.g., the expensive tumor imaging or biopsy procedures needed to evaluate treatment effects. Therefore, it becomes essential to actively incorporate more high-quality labeled data, all while adhering to a constrained labeling budget. To enable data-efficient treatment effect estimation, we formalize the problem through rigorous theoretical analysis within the active learning context, where the derived key measures -- factual and counterfactual covering radii determine the risk upper bound. To reduce the bound, we propose a greedy radius reduction algorithm, which excels under an idealized, balanced data distribution. To generalize to more realistic data distributions, we further propose FCCM, which transforms the optimization objective into the Factual and Counterfactual Coverage Maximization to ensure effective radius reduction during data acquisition. Furthermore, benchmarking FCCM against other baselines demonstrates its superiority across both fully synthetic and semi-synthetic datasets. Code: https://github.com/uqhwen2/FCCM.

Social Aspects · Accountability, Transparency, and Interpretability

Kento Nishi, Rahul Ramesh, Maya Okawa, Mikail Khona, Hidenori Tanaka, Ekdeep Singh Lubana

Knowledge Editing (KE) algorithms alter models' weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations. However, recent work has shown that applying KE can adversely affect models' broader factual recall accuracy and diminish their reasoning abilities. Although these studies give insights into the potential harms of KE algorithms, e.g., performance evaluations on benchmarks, little is understood about why such destructive failures occur. Motivated by this, we define a novel synthetic task in which a Transformer is trained from scratch to internalize a "structured" knowledge graph. The structure enforces relationships between entities of the graph, such that editing a factual association has "trickling effects" on other entities (e.g., altering X's parent is Y to Z affects who X's siblings' parent is). Through evaluations of edited models on this task, we show that KE inadvertently affects representations of entities beyond the targeted one, distorting relevant structures that allow a model to infer unseen knowledge about an entity. We call this phenomenon representation shattering and demonstrate that it degrades models' factual recall and reasoning performance. We further corroborate our findings in naturalistic settings with pre-trained Llama and Mamba models as well. Overall, our work yields a precise mechanistic hypothesis to explain why KE has adverse effects on model abilities.

Deep Learning · Large Language Models

Phillip Guo, Aaquib Syed, Abhay Sheshadri, Aidan Ewart, Gintare Karolina Dziugaite

Methods for knowledge editing and unlearning in large language models seek to edit or remove undesirable knowledge or capabilities without compromising general language modeling performance. This work investigates how mechanistic interpretability---which, in part, aims to identify model components (circuits) associated to specific interpretable mechanisms that make up a model capability---can improve the precision and effectiveness of editing and unlearning. We find a stark difference in unlearning and edit robustness when training components localized by different methods. We highlight an important distinction between methods that localize components based primarily on preserving outputs, and those finding high level mechanisms with predictable intermediate states. In particular, localizing edits/unlearning to components associated with the *lookup-table mechanism* for factual recall 1) leads to more robust edits/unlearning across different input/output formats, and 2) resists attempts to relearn the unwanted information, while also reducing unintended side effects compared to baselines, on both a sports facts dataset and the CounterFact dataset across multiple models.We also find that certain localized edits disrupt the latent knowledge in the model more than any other baselines, making unlearning more robust to various attacks.

Deep Learning · Large Language Models

Vincent-Pierre Berges, Barlas Oğuz, Daniel HAZIZA, Scott Yih, Luke Zettlemoyer, Gargi Ghosh

Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense feed-forward layers, providing dedicated capacity to store and retrieve information cheaply. This work takes memory layers beyond proof-of-concept, proving their utility at contemporary scale. On downstream tasks, language models augmented with our improved memory layer outperform dense models with more than twice the computation budget, as well as mixture-of-expert models when matched for both compute and parameters. We find gains are especially pronounced for factual tasks. We provide a fully parallelizable memory layer implementation, demonstrating scaling laws with up to 128B memory parameters, pretrained to 1 trillion tokens, comparing to base models with up to 8B parameters.

Deep Learning · Large Language Models

Zhichen Dong, Zhanhui Zhou, Zhixuan Liu, Chao Yang, Chaochao Lu

In this work, we argue that large language models (LLMs), though trained to predict only the next token, exhibit emergent planning behaviors: $\textbf{their hidden representations encode future outputs beyond the next token}$. Through simple probing, we demonstrate that LLM prompt representations encode global attributes of their entire responses, including $\textit{structure attributes}$ (e.g., response length, reasoning steps), $\textit{content attributes}$ (e.g., character choices in storywriting, multiple-choice answers at the end of response), and $\textit{behavior attributes}$ (e.g., answer confidence, factual consistency). In addition to identifying response planning, we explore how it scales with model size across tasks and how it evolves during generation. The findings that LLMs plan ahead for the future in their hidden representations suggest potential applications for improving transparency and generation control.

Deep Learning · Large Language Models

Albert Gong, Kamilė Stankevičiūtė, Chao Wan, Anmol Kabra, Raphael Thesmar, Johann Lee, Julius Klenke, Carla Gomes, Kilian Weinberger

High-quality benchmarks are essential for evaluating reasoning and retrieval capabilities of large language models (LLMs). However, curating datasets for this purpose is not a permanent solution as they are prone to data leakage and inflated performance results. To address these challenges, we propose PhantomWiki: a pipeline to generate unique, factually consistent document corpora with diverse question-answer pairs. Unlike prior work, PhantomWiki is neither a fixed dataset, nor is it based on any existing data. Instead, a new PhantomWiki instance is generated on demand for each evaluation. We vary the question difficulty and corpus size to disentangle reasoning and retrieval capabilities, respectively, and find that PhantomWiki datasets are surprisingly challenging for frontier LLMs. Thus, we contribute a scalable and data leakage-resistant framework for disentangled evaluation of reasoning, retrieval, and tool-use abilities.

Social Aspects · Accountability, Transparency, and Interpretability

Zhan Qu, Daniel Gomm, Michael Färber

Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy—Counterfactual Explainer for Dynamic Graphs—a model-agnostic, instance-level explanation approach that identifies counterfactual subgraphs to interpret TGNN predictions. CoDy employs a search algorithm that combines Monte Carlo Tree Search with heuristic selection policies, efficiently exploring a vast search space of potential explanatory subgraphs by leveraging spatial, temporal, and local event impact information. Extensive experiments against state-of-the-art factual and counterfactual baselines demonstrate CoDy's effectiveness, with improvements of 16% in AUFSC+ over the strongest baseline. Our code is available at: https://github.com/daniel-gomm/CoDy

Deep Learning · Foundation Models

Yuanchen Wu, Ke Yan, Shouhong Ding, Ziyin Zhou, Xiaoqiang Li

Large Vision-Language Models (LVLMs) have manifested strong visual question answering capability. However, they still struggle with aligning the rationale and the generated answer, leading to inconsistent reasoning and incorrect responses. To this end, this paper introduces Self-Rationale Calibration (SRC) framework to iteratively calibrate the alignment between rationales and answers. SRC begins by employing a lightweight “rationale fine-tuning” approach, which modifies the model’s response format to require a rationale before deriving answer without explicit prompts. Next, SRC searches a diverse set of candidate responses from the fine-tuned LVLMs for each sample, followed by a proposed pairwise scoring strategy using a tailored scoring model, R-Scorer, to evaluate both rationale quality and factual consistency of candidates. Based on a confidence-weighted preference curation process, SRC decouples the alignment calibration into a preference fine-tuning manner, leading to significant improvements of LVLMs in perception, reasoning, and generalization across multiple benchmarks. Our results emphasize the rationale-oriented alignment in exploring the potential of LVLMs.

Applications · Computer Vision

Saehyung Lee, Seunghyun Yoon, Trung Bui, Jing Shi, Sungroh Yoon

Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations. Our analysis reveals that existing hallucination detection methods struggle with detailed captions. We attribute this to the increasing reliance of MLLMs on their generated text, rather than the input image, as the sequence length grows. To address this issue, we propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions. Additionally, we introduce an evaluation framework and a benchmark dataset to facilitate the systematic analysis of detailed captions. Our experiments demonstrate that the proposed evaluation method aligns better with human judgments of factuality than existing metrics. Moreover, we show that current approaches for enhancing MLLM factuality often fail in hyper-detailed image captioning tasks. In contrast, our approach significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V. Finally, we highlight a limitation of VQA-centric benchmarking by demonstrating that an MLLM's performance on VQA benchmarks may not correlate with its ability to generate detailed image captions.