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 2508.17225cs.CLcs.AI
SSFO：面向检索增强生成的自监督忠实性优化
SSFO: Self-Supervised Faithfulness Optimization for Retrieval-Augmented Generation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Chinese Academy of Sciences（中国科学院）；Shanghai AI Lab（上海人工智能实验室）；Tencent Hunyuan（腾讯文英）
Retrieval-Augmented Generation (RAG) systems require Large Language Models (LLMs) to generate responses that are faithful to the retrieved context. However, faithfulness hallucination remains a critical challenge, as existing methods often require costly supervision and post-training or significant inference burdens. To overcome these limitations, we introduce Self-Supervised Faithfulness Optimization (SSFO), the first self-supervised alignment approach for enhancing RAG faithfulness. SSFO constructs preference data pairs by contrasting the model's outputs generated with and without the context. Leveraging Direct Preference Optimization (DPO), SSFO aligns model faithfulness without incurring labeling costs or additional inference burden. We theoretically and empirically demonstrate that SSFO leverages a benign form of \emph{likelihood displacement}, transferring probability mass from parametric-based tokens to context-aligned tokens. Based on this insight, we propose a modified DPO loss function to encourage likelihood displacement. Comprehensive evaluations show that SSFO significantly outperforms existing methods, achieving state-of-the-art faithfulness on multiple context-based question-answering datasets. Notably, SSFO exhibits strong generalization, improving cross-lingual faithfulness and preserving general instruction-following capabilities. We release our code and model at the anonymous link: https://github.com/chkwy/SSFO
Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation
Air University（空军大学）；National University of Sciences and Technology (NUST)（国家科学技术大学）；University of Oklahoma（俄克拉荷马大学）；Lahore University of Management Sciences (LUMS)（拉合尔管理科学大学）
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
School of Computer Science and Engineering, Northeastern University, China（东北大学计算机科学与工程学院）；Department of Computer Science and Technology, Institute for AI, Tsinghua University, China（清华大学人工智能研究院计算机科学与技术系）；Microsoft Research Asia, Beijing, China（微软亚洲研究院）；Language Technologies Institute, Carnegie Mellon University, United States（卡内基梅隆大学语言技术研究所）
Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
Wangxuan Institute of Computer Technology, Peking University（王轩计算机技术研究所，北京大学）；Institute of Artificial Intelligence and Future Networks, Beijing Normal University（人工智能与未来网络研究院，北京师范大学）
5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
University of Information Technology, Ho Chi Minh City, Vietnam（信息技术大学，胡志明市，越南）；Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam（越南胡志明市国家大学，胡志明市，越南）
Context-DPO: Aligning Language Models for Context-Faithfulness
University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Corporation（微软公司）；University of California, Merced（加州大学默塞德分校）；National University of Singapore（新加坡国立大学）
When Do Explanations Help In-Context Learning? A Comparative Study of Natural Language Explanation Types and Faithfulness
LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；Imperial College London（伦敦帝国学院）；Technical University of Munich（慕尼黑工业大学）；MaiNLP lab, CIS, LMU Munich（慕尼黑大学CIS研究所MaiNLP实验室）
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
School of Informatics, Xiamen University（厦门大学信息学院）；The Hong Kong Polytechnic University（香港理工大学）；University of Chinese Academy of Sciences（中国科学院大学）；Alibaba Group（阿里巴巴集团）；Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室（厦门大学），中华人民共和国文化和旅游部，中国）
Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs
Shanghai Jiao Tong University（上海交通大学）；The Hong Kong University of Science and Technology（香港科技大学）；The Australian National University（澳大利亚国立大学）；Fudan University（复旦大学）；University of Sydney（悉尼大学）
Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Models
Universitas Islam Riau（廖内伊斯兰大学）；Universitas Lancang Kuning（兰昌坤宁大学）；Izmir Katip Celebi University（伊兹密尔卡蒂普·切莱比大学）；Ritsumeikan University（立命馆大学）；Universiti Islam Antarabangsa Tuanku Syed Sirajuddin (UniSIRAJ)（端姑赛德·西拉鲁丁国际伊斯兰大学（UniSIRAJ））；International Islamic University Malaysia（马来西亚国际伊斯兰大学）
Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS
Chongqing University（重庆大学）；Queen Mary University of London（伦敦玛丽女王大学）；Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing（重庆市大数据智能与隐私计算重点实验室）；Fangda Partners（方达律师事务所）
SpatialChain: A Benchmark for Auditing Spatial Reasoning Faithfulness in VLMs
Universidade Federal de Mato Grosso (UFMT)（马托格罗索联邦大学）；Universidade Federal de Goiás (UFG)（戈亚斯联邦大学）；Advanced Knowledge Center for Immersive Technologies (AKCIT)（沉浸式技术高级知识中心）
Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Artificial Intelligence Laboratory, China Mobile Communication Group Tianjin Co., Ltd.（中国移动通信集团天津有限公司人工智能实验室）；University College London（伦敦大学学院）
CLAIR-Fin: An Adversarial Multi-Agent Framework for Claim-Level Verification and Adaptive Debate in Cross-Modal Financial QA
Ahsanullah University of Science and Technology（阿萨努拉科技大学）；Jashore University of Science and Technology（杰索尔科技大学）；American International University - Bangladesh（孟加拉国美国国际大学）
Peking University（北京大学）；Chinese Academy of Sciences（中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Pengcheng Laboratory（鹏城实验室）
In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record. We thus try to evaluate the generation faithfulness with two entity-centric metrics: table record coverage and the ratio of hallucinated entities in text, both of which are shown to have strong agreement with human judgements. Then based on these metrics, we quantitatively analyze the correlation between training data quality and generation fidelity which indicates the potential usage of entity information in faithful genera…
