通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。通知：联邦节假日调休：哥伦布日 / 原住民日（Columbus Day / Indigenous Peoples' Day），今日（13日）无更新。
arXiv 2504.14858cs.AIcs.CL
检索是不够的：通过测试时批评与优化增强RAG推理
Retrieval is Not Enough: Enhancing RAG Reasoning through Test-Time Critique and Optimization
Zhejiang University（浙江大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；South China University of Technology（华南理工大学）；University of British Columbia（不列颠哥伦比亚大学）；Fudan University（复旦大学）；University of Hong Kong（香港大学）
Jiaqi Wei, Hao Zhou, Xiang Zhang, Di Zhang, Zijie Qiu, Wei Wei, Jinzhe Li, Wanli Ouyang, Siqi Sun
Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the evidence retrieved, leading to factual inconsistencies or unsupported conclusions. In this work, we reinterpret RAG as Retrieval-Augmented Reasoning and identify a central but underexplored problem: Reasoning Misalignment -- the divergence between an LLM's internal reasoning trajectory and the evidential constraints provided by retrieval. To address this issue, we propose AlignRAG, a novel iterative framework grounded in Critique-Driven Alignment (CDA). We further introduce AlignRAG-auto, an autonomous variant that dynamically terminates refinement, removing the need to pre-specify the number of critique iterations. At the heart of AlignRAG lies a contrastive critique synthesis mechanism that generates retrieval-sensitive critiques while mitigating self-bias. This mechanism trains a dedicated retrieval-augmented Critic Language Model (CLM) using labeled critiques that distinguish between evidence-aligned and misaligned reasoning. Empirical evaluations show that our approach significantly improves reasoning fidelity. Our 8B-parameter CLM improves performance over the Self-Refine baseline by 12.1% on out-of-domain tasks and outperforms a standard 72B-parameter CLM by 2.2%. Furthermore, AlignRAG-auto achieves this state-of-the-art performance while dynamically determining the optimal number of refinement steps, enhancing efficiency and usability. AlignRAG remains compatible with existing RAG architectures as a plug-and-play module and demonstrates strong robustness under both informative and noisy retrieval scenarios.
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
Knight Foundation School of Computing and Information Sciences（骑士基金会计算与信息科学学院）；Florida International University（佛罗里达国际大学）；College of Engineering（工程学院）；University of South Florida（佛罗里达州立大学）
From RAG to Agentic: Validating Islamic-Medicine Responses with LLM Agents
Mohamed bin Zayed University of Artificial Intelligence, UAE（阿布扎克穆罕默德·本·扎耶德人工智能大学）；Edinburgh Napier University, UK（爱丁堡纳皮尔大学）；VIT Bhopal University, India（比哈尔大学）
RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
University of New South Wales（新南威尔士大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Mohamed Bin Zayed University of Artificial Intelligence（莫扎伊德大学人工智能学院）；Technology Innovation Institute（技术创新研究所）
Towards Platonic Representation for Table Reasoning: A Foundation for Permutation-Invariant Retrieval
Department of Mathematics and Data Science, Vrije Universiteit Brussel (VUB)（瓦隆公国布鲁塞尔自由大学数学与数据科学系）；Data Science Lab, Royal Library of Belgium (KBR)（比利时皇家图书馆数据科学实验室）
