RAG / 检索增强生成

Generation of Asset Administration Shell with Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0

Yuchen Xia, Zhewen Xiao, Nasser Jazdi, Michael Weyrich

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

Comments Published in IEEE Access

WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia

Yufang Hou, Alessandra Pascale, Javier Carnerero-Cano, Tigran Tchrakian, Radu Marinescu, Elizabeth Daly, Inkit Padhi, Prasanna Sattigeri

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

FinBen: A Holistic Financial Benchmark for Large Language Models

Qianqian Xie, Weiguang Han, Zhengyu Chen, Ruoyu Xiang, Xiao Zhang, Yueru He, Mengxi Xiao, Dong Li, Yongfu Dai, Duanyu Feng, Yijing Xu, Haoqiang Kang, Ziyan Kuang, Chenhan Yuan, Kailai Yang, Zheheng Luo, Tianlin Zhang, Zhiwei Liu, Guojun Xiong, Zhiyang Deng, Yuechen Jiang, Zhiyuan Yao, Haohang Li, Yangyang Yu, Gang Hu, Jiajia Huang, Xiao-Yang Liu, Alejandro Lopez-Lira, Benyou Wang, Yanzhao Lai, Hao Wang, Min Peng, Sophia Ananiadou, Jimin Huang

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments 26 pages, 11 figures

Designing an Evaluation Framework for Large Language Models in Astronomy Research

John F. Wu, Alina Hyk, Kiera McCormick, Christine Ye, Simone Astarita, Elina Baral, Jo Ciuca, Jesse Cranney, Anjalie Field, Kartheik Iyer, Philipp Koehn, Jenn Kotler, Sandor Kruk, Michelle Ntampaka, Charles O'Neill, Joshua E. G. Peek, Sanjib Sharma, Mikaeel Yunus

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.AI

Comments 7 pages, 3 figures. Code available at https://github.com/jsalt2024-evaluating-llms-for-astronomy/astro-arxiv-bot

Towards Robustness of Text-to-Visualization Translation against Lexical and Phrasal Variability

Jinwei Lu, Yuanfeng Song, Haodi Zhang, Chen Zhang, Raymond Chi-Wing Wong

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

IITK at SemEval-2024 Task 2: Exploring the Capabilities of LLMs for Safe Biomedical Natural Language Inference for Clinical Trials

Shreyasi Mandal, Ashutosh Modi

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments Accepted at SemEval 2024, NAACL 2024; 8 Pages

FACTOID: FACtual enTailment fOr hallucInation Detection

Vipula Rawte, S. M Towhidul Islam Tonmoy, Krishnav Rajbangshi, Shravani Nag, Aman Chadha, Amit P. Sheth, Amitava Das

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Evaluating Very Long-Term Conversational Memory of LLM Agents

Adyasha Maharana, Dong-Ho Lee, Sergey Tulyakov, Mohit Bansal, Francesco Barbieri, Yuwei Fang

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments 19 pages; Project page: https://snap-research.github.io/locomo/

Large Multi-Modal Models (LMMs) as Universal Foundation Models for AI-Native Wireless Systems

Shengzhe Xu, Christo Kurisummoottil Thomas, Omar Hashash, Nikhil Muralidhar, Walid Saad, Naren Ramakrishnan

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

How well do LLMs cite relevant medical references? An evaluation framework and analyses

Kevin Wu, Eric Wu, Ally Cassasola, Angela Zhang, Kevin Wei, Teresa Nguyen, Sith Riantawan, Patricia Shi Riantawan, Daniel E. Ho, James Zou

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately

Liang Zhang, Katherine Jijo, Spurthi Setty, Eden Chung, Fatima Javid, Natan Vidra, Tommy Clifford

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Weaver: Foundation Models for Creative Writing

Tiannan Wang, Jiamin Chen, Qingrui Jia, Shuai Wang, Ruoyu Fang, Huilin Wang, Zhaowei Gao, Chunzhao Xie, Chuou Xu, Jihong Dai, Yibin Liu, Jialong Wu, Shengwei Ding, Long Li, Zhiwei Huang, Xinle Deng, Teng Yu, Gangan Ma, Han Xiao, Zixin Chen, Danjun Xiang, Yunxia Wang, Yuanyuan Zhu, Yi Xiao, Jing Wang, Yiru Wang, Siran Ding, Jiayang Huang, Jiayi Xu, Yilihamu Tayier, Zhenyu Hu, Yuan Gao, Chengfeng Zheng, Yueshu Ye, Yihang Li, Lei Wan, Xinyue Jiang, Yujie Wang, Siyu Cheng, Zhule Song, Xiangru Tang, Xiaohua Xu, Ningyu Zhang, Huajun Chen, Yuchen Eleanor Jiang, Wangchunshu Zhou

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Evaluating and Enhancing Large Language Models Performance in Domain-specific Medicine: Osteoarthritis Management with DocOA

Xi Chen, MingKe You, Li Wang, WeiZhi Liu, Yu Fu, Jie Xu, Shaoting Zhang, Gang Chen, Kang Li, Jian Li

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments 16 Pages, 7 Figures

Minimizing Factual Inconsistency and Hallucination in Large Language Models

Muneeswaran I, Shreya Saxena, Siva Prasad, M V Sai Prakash, Advaith Shankar, Varun V, Vishal Vaddina, Saisubramaniam Gopalakrishnan

专题命中 RAG评测 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking

Lefteris Loukas, Ilias Stogiannidis, Odysseas Diamantopoulos, Prodromos Malakasiotis, Stavros Vassos

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments Long paper accepted to ACM ICAIF-23

RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation

RENDER：控制LLM记忆评估中面向读者的证据

Yuan Si, Simeng Han, Daming Li, Jialu Zhang

机构 * University of Waterloo（滑铁卢大学） ； Stanford University（斯坦福大学） 纠错

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 RENDER是控制LLM记忆评估中面向读者证据的基准，实验显示其相关数据包比原始对话表现更优，效果可迁移，提示需关注评估中的读者面向人工制品。

LLM Enhancement with Domain Expert Mental Model to Reduce LLM Hallucination with Causal Prompt Engineering

结合领域专家心智模型的大语言模型增强：通过因果提示工程减少大语言模型幻觉

Boris Kovalerchuk, Brent D. Fegley

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 本文提出结合专家心智模型（EMM）的因果提示工程框架，通过形式化相关前置流程构建EMM，减少LLM幻觉，在三类任务中验证了方法有效性。

Comments 42 pages,4 figures, 4 tables

Clause Encounters of the Third Kind: Can LLMs Replace Language Teachers?

条款式的第三类接触：大型语言模型能否替代语言教师？

Kristina Šekrst, Ana Kovačić

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract_cn)；分类 cs.CL

AI总结 该研究评估了LLM替代语言教师提供教学反馈与解释的能力，发现其纠错能力出色但教学解释不足，AI辅助语言学习热情或超出对其教学能力的认知。

Journal ref Oxford Intersections: AI in Society (Oxford, online edn, Oxford Academic, 20 Mar. 2025 - )

FDABench: A Benchmark for Data Agents on Analytical Queries over Heterogeneous Data

FDABench：异构数据上分析查询的数据代理基准

Ziting Wang, Shize Zhang, Haitao Yuan, Jinwei Zhu, Wei Dong, Gao Cong

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.DB

AI总结 提出FDABench基准，通过2007个任务覆盖六种数据模态，并设计PUDDING框架自动构建数据集，以评估数据代理在异构数据上的推理能力。

Comments Accepted to KDD'26

MemoryLake on MemoryArena: A Matched Study of Agent Memory Backends

基于MemoryArena的MemoryLake研究：智能体记忆后端的匹配对比

Chaoqun Zhan, Qiang Zhou, Guannan Li, Zhenqiang Huang, Qianjin Wang

机构 * MemoryLake Team（MemoryLake团队） 纠错

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 该研究在MemoryArena的五个任务领域中，对比MemoryLake等三种智能体记忆后端，发现MemoryLake在数学等三个领域成功率最高，整体平均成功率领先，且性能与工作负载相关。

Comments 16 pages, 7 tables

Reconcile Once, Write Anytime: A Trust-Tiered Librarian and a Multi-Agent Writer for Drift-Free, Point-in-Time Research

一次对账，随时撰写：用于无漂移、时点研究的信任分层图书馆与多智能体撰写器

Xing Zhang, Yanwei Cui, Guanghui Wang, Peiyang He

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.CL

AI总结 该研究提出双层智能体系统，通过信任分层图书馆与多智能体撰写器分离知识库与报告撰写，消除报告矛盾与漂移，实验验证其在多指标、多场景下的有效性与效率优势。

Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents

多层架构中的防御效果：对持久内存攻击状态机LLM代理的机制性评估

Jun Wen Leong

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 本文评估了六种防御措施在九个开源模型上的延迟触发攻击效果，发现输入级和检索级过滤器效果不佳，而内存层工具门控（Memory Sandbox）显著降低攻击成功率，揭示了不同防御类别的失效原因。

Comments v4: Added double dissociation (reasoning-mode ablation), content-layer defense (RATG), loaded-corpus frontier evaluation (21 models, 3 providers, N=40), 7B judge capability bound, reproducibility validity criterion, ethics/disclosure statement. Gemini 3.1 Pro Preview 95% ASR; GPT-5.1 regression (22.5%); tripartite vendor divergence. Code: github.com/junwenleong/stateful-agent-security-eval

GuideSkill: Evolving Executable LLM Agent Skills for Guideline-Grounded Clinical Reasoning

GuideSkill：面向基于指南的临床推理的可执行大语言模型智能体技能演化框架

Lang Cao, Yuhao Shen, Tianyang Luo, Simo Du, Hao Peng, Yue Guo

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 本文提出与模型无关的GuideSkill框架，通过可执行技能结合指南流程与病例诊断模式，在多基准和骨干模型上显著提升临床推理性能，技能可靠且实用。

Does Faithfulness-Guided Alignment Hurt Accuracy? Unlocking Accurate and Faithful Post-Retrieval Reasoning

CRAFT: 通过强化学习进行多跳问答的校准推理与答案忠实轨迹

Yu Liu, Wenxiao Zhang, Diandian Guo, Cong Cao, Fangfang Yuan, Qiang Sun, Yanbing Liu, Jin B. Hong, Zhiyuan Ma

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.CL

AI总结 CRAFT通过强化学习框架提升多跳问答的推理准确性和答案忠实度，结合确定性奖励和判官奖励，增强推理轨迹的可审计性与语义一致性。

Verifier-First Evaluation of Agentic LLMs for Infrastructure-as-Code Generation

用于基础设施即代码生成的智能语言模型的验证优先评估

Mohamed Jouini

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 研究针对自然语言生成基础设施即代码的问题，对七种智能策略在特定基准测试上进行验证优先评估，通过多种方法得出如主动检索提升性能、迭代优化有收敛效果等五个主要发现，为相关研究提供了重要参考。

Comments 26 pages, 3 figures, 17 tables. Benchmark dataset available at https://huggingface.co/datasets/iac-eval-v2/iac-eval-v2

OntoExtend: A Framework for Requirement-driven and Scalable Ontology Extension with LLMs

OntoExtend：一个用于基于需求驱动和可扩展的大语言模型本体扩展框架

Anna Sofia Lippolis, Mohammad Javad Saeedizade, Stefan Schmid, Simon Blattner, Robin Keskisärkkä, Aldo Gangemi, Eva Blomqvist, Andrea Giovanni Nuzzolese

机构 * Linköping University（林雪平大学） ； University of Bologna（博洛尼亚大学） ； Bosch（博世公司） ； ISTC-CNR（意大利国家研究委员会信息科学与技术研究所） 纠错

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI

AI总结 研究基于需求驱动的本体扩展问题，提出用检索增强生成的OntoExtend框架，通过在相关输入本体和需求上应用该框架，在两个用例的能力问题上评估，结果显示其可作为现实场景中本体扩展起草助手，对问题特异性和建模概要敏感。

Comments Accepted in research track of Semantics 2026: https://2026-eu.semantics.cc/page/accepted_research

Optimizing Visibility in Generative Engines: A Critical Survey of Generative Engine Optimization (2023-2026)

优化生成引擎中的可见性：生成引擎优化的批判性综述（2023 - 2026）

Olivier Martinez

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.IR

AI总结 该研究对2023年11月至2026年有关生成引擎优化的45项研究进行批判性综述，指出其术语等存在异质性。贡献多阶段形式模型等，表明虽有成果但证据有限，未显示技术对有机可发现性等有稳定因果效应。

Comments 18 pages, 8 tables, 1 figure; critical survey of 45 studies; ancillary literature matrix and search protocol included

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

首先，不伤害：迈向临床安全的大语言模型

David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj, Priyank Jain, Jessica Tran, Matthew Gwiazdon, Arjun Rustagi, Jenelle Jindal, Jacob M. Koshy, Vinay Kadiyala, Anup Agarwal, Bassman Tappuni, Brianna French, Sirus Jesudasen, Christopher V. Cosgriff, Rebanta Chakraborty, Jillian Caldwell, Susan Ziolkowski, David J. Iberri, Robert Diep, Rahul S. Dalal, Kira L. Newman, Kristin Galetta, J. Carl Pallais, Nancy Wei, Kathleen M. Buchheit, David I. Hong, Vartan Pahalyants, Ernest Y. Lee, Allen Shih, Tamara B. Kaplan, Vishnu Ravi, Sarita Khemani, Thomas A. Buckley, April S. Liang, Daniel Shirvani, Advait Patil, Nicholas Marshall, Kanav Chopra, Joel Koh, Adi Badhwar, Anastasia Perez, Austin J. Schoeffler, Mahbuba Tusty, Chase M. Walton, Liam G. McCoy, David J. H. Wu, Yingjie Weng, Sumant Ranji, Kevin Schulman, Nigam H. Shah, Jason Hom, Arnold Milstein, Arjun K. Manrai, Adam Rodman, Jonathan H. Chen, Ethan Goh

机构 * Harvard Combined Dermatology Program（哈佛联合皮肤科项目） ； Department of Dermatology, Mass General Brigham（麻省总医院皮肤科） ； Harvard Medical School（哈佛医学院） ； Stanford Center for Biomedical Informatics Research（斯坦福生物医学信息学研究中心） ； Stanford University（斯坦福大学） ； Division of Hospital Medicine, Department of Medicine, Stanford University School of Medicine（斯坦福大学医学院医院医学科） ； Department of Medicine, Cambridge Health Alliance（剑桥健康联盟医学科） ； Beth Israel Deaconess Hospital–Plymouth（贝塞斯达德acons医院-普利茅斯） ； Department of Medicine, University of California, San Francisco（加州大学旧金山分校医学科） ； Department of Neurology, Stanford University School of Medicine（斯坦福大学医学院神经科） ； Department of Medicine, Beth Israel Deaconess Medical Center（贝塞斯达德acons医学中心医学科） ； Division of Cardiology, Department of Medicine, Cambridge Health Alliance（剑桥健康联盟心脏病科） ； Department of Cardiovascular Medicine, Summa Health System（Summa健康系统心血管医学科） ； Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, University of Wisconsin-Madison（威斯康星大学麦迪逊分校医学科过敏、呼吸科和危重医学科） ； Division of Pulmonary and Critical Care Medicine, Department of Medicine, Massachusetts General Hospital（麻省总医院呼吸科和危重医学科） ； Center for Immunology and Inflammatory Diseases, Department of Medicine, Massachusetts General Hospital（麻省总医院免疫和炎症疾病中心） ； Broad Institute of MIT and Harvard（MIT和哈佛Broad研究所） ； Division of Pulmonary, Critical Care, and Sleep Medicine, Cambridge Health Alliance（剑桥健康联盟呼吸科、危重医学科和睡眠医学科） 纠错

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI

AI总结 提出NOHARM基准，包含1100个初级到专科咨询案例，评估28个LLM的医疗建议安全性，发现高达22.6%的案例存在严重危害风险，其中遗漏错误占80%以上。

Toward Trustworthy Large Language Model Agents in Healthcare

迈向医疗保健领域值得信赖的大语言模型智能体

Hadi Hasan, Safaa Salman, Adam Tai Abou Dargham, Ammar Mohanna, Ali Chehab

专题命中 RAG评测 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI

AI总结 针对医疗预约调度瓶颈，提出CareConnect智能体，利用大语言模型函数调用等技术，协调工具支持预约操作，设安全护栏。经评估有高任务完成率、安全合规性及成本效益，能自动化复杂医疗工作流程。

CLAP: Closed-Loop Training, Evaluation, and Release Control for Domain Agent Post-training

CLAP：领域智能体后训练的闭环训练、评估与发布控制

Fangfei Li, Chenyang Zhao, Long Wang, Feng Tian, Zhiyue Zheng, Lv Guo

机构 * MatrixOrigin（矩阵起源） 纠错

专题命中 RAG评测 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 提出CLAP闭环方法，通过数据验证、奖励/KL诊断、离线门控和应用链回放，在制造场景中评估后训练效果，发现仅部分批次提升且存在KL风险，支持集成循环管理。

Comments 6 pages, 1 figure. Accepted to CRAE 2026; to appear in SPIE Proceedings. Best Poster Award