RAG / 检索增强生成

Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations

超越化学问答：利用模块化化学操作评估LLM的化学推理

Hao Li, He Cao, Bin Feng, Yanjun Shao, Xiangru Tang, Zhiyuan Yan, Li Yuan, Yonghong Tian, Yu Li

机构 * Pengcheng Laboratory（鹏城实验室） ； International Digital Economy Academy（国际数字经济学院） ； School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院） ； School of AI for Science, Peking University（北京大学科学人工智能学院） ； Yale University（耶鲁大学） 纠错

专题命中 知识库问答 ：knowledge retrieval(abstract)；分类 cs.AI

AI总结 本文提出ChemCoTBench框架，通过模块化化学操作评估LLM在化学推理中的能力，解决分子优化和反应预测等复杂任务。

Comments Accepted by NeurIPS 2025 Dataset Track, 22 pages, 10 figures

Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends

多跳问答中的检索-推理过程：一种四维设计框架和实证趋势

Yuelyu Ji, Zhuochun Li, Rui Meng, Daqing He

机构 * School of Computing and Information, University of Pittsburgh（计算与信息学院，匹兹堡大学） ； Google Cloud AI Research（谷歌云人工智能研究） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

AI总结 本文提出四维设计框架，分析多跳问答系统中检索-推理过程的执行计划、索引结构、控制策略和停止标准，揭示有效性、效率与证据忠实度的权衡，并指出结构感知规划、可转移控制策略和鲁棒停止是未来挑战。

SportsGPT: An LLM-driven Framework for Interpretable Sports Motion Assessment and Training Guidance

SportsGPT: 一种基于大语言模型的可解释性体育动作评估与训练指导框架

Wenbo Tian, Ruting Lin, Hongxian Zheng, Yaodong Yang, Geng Wu, Zihao Zhang, Zhang Zhang

机构 * School of Artificial Intelligence, UCAS, Beijing, China（人工智能学院） ； MAIS, NLPR, Institute of Automation, CAS, Beijing, China（自动化研究所） ； College of Education, Beijing Sport University, Beijing, China（北京体育大学） ； KuTi Sports Technology, Shaanxi, China（KuTi体育科技） ； Haoxiong Technology, Shanghai, China（浩鸿科技） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.AI

AI总结 SportsGPT通过结合大语言模型和运动分析技术，实现可解释的体育动作评估与专业训练指导。

Chain-of-Conceptual-Thought Elicits Daily Conversation in Large Language Models

Qingqing Gu, Dan Wang, Yue Zhao, Xiaoyu Wang, Zhonglin Jiang, Yong Chen, Hongyan Li, Luo Ji

机构 * Geely AI Lab（Geely人工智能实验室） ； Beijing Institute of Technology（北京理工大学） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

Comments PRICAI 2025

Capability Ceilings in Autoregressive Language Models: Empirical Evidence from Knowledge-Intensive Tasks

Javier Marín

专题命中 知识库问答 ：knowledge retrieval(abstract)；分类 cs.AI

Comments The experiments in this paper were performed in January 2024. Current model architectures are considerably more complex than those presented here

SustainableQA: A Comprehensive Question Answering Dataset for Corporate Sustainability and EU Taxonomy Reporting

Mohammed Ali, Abdelrahman Abdallah, Adam Jatowt

专题命中 知识库问答 ：RAG(abstract)；分类 cs.IR

JGU Mainz's Submission to the WMT25 Shared Task on LLMs with Limited Resources for Slavic Languages: MT and QA

Hossain Shaikh Saadi, Minh Duc Bui, Mario Sanz-Guerrero, Katharina von der Wense

机构 * Johannes Gutenberg University Mainz（莱茵河畔明斯特约翰·格门特大学） ； University of Colorado Boulder（科罗拉多大学波尔德分校） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.CL

Comments WMT 25 Shared Task LLMs with Limited Resources for Slavic Languages: MT and QA

Beyond Stars: Bridging the Gap Between Ratings and Review Sentiment with LLM

Najla Zuhir, Amna Mohammad Salim, Parvathy Premkumar, Moshiur Farazi

机构 * College of Computing & Information Technology University of Doha for Science and Technology（计算与信息科技学院 优德科技大学） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.AI

Comments Paper accepted for presentation at ACS/IEEE 22nd International Conference on Computer Systems and Applications (AICCSA 2025)

Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards

Jaehoon Yun, Jiwoong Sohn, Jungwoo Park, Hyunjae Kim, Xiangru Tang, Yanjun Shao, Yonghoe Koo, Minhyeok Ko, Qingyu Chen, Mark Gerstein, Michael Moor, Jaewoo Kang

机构 * Korea University（韩国大学） ； ETH Zürich（苏黎世联邦理工学院） ； Yale University（耶鲁大学） ； AIGEN Sciences（AIGEN公司） ； Hanyang University College of Medicine（翰雅大学医学院） ； University of Ulsan College of Medicine（釜山大学医学院） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.CL

Comments Accepted to EMNLP 2025 (Oral)

A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering

Zhiyue Liu, Sihang Liu, Jinyuan Liu, Xinru Zhang

机构 * School of Computer, Electronics and Information（计算机、电子与信息学院） ； Guangxi University（广西大学） ； Guangxi Key Laboratory of Multimedia Communications and Network Technology（广西多媒体通信与网络技术重点实验室） 纠错

专题命中 知识库问答 ：knowledge retrieval(abstract)；分类 cs.AI

Comments Accepted by the IEEE International Conference on Multimedia and Expo (ICME 2025) for oral presentation. © 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

How to Make Museums More Interactive? Case Study of Artistic Chatbot

Filip J. Kucia, Bartosz Grabek, Szymon D. Trochimiak, Anna Wróblewska

专题命中 知识库问答 ：RAG(abstract)；分类 cs.IR

Comments 7 pages, 3 figures

MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge

Jie He, Nan Hu, Wanqiu Long, Jiaoyan Chen, Jeff Z. Pan

机构 * School of Informatics, University of Edinburgh, UK（爱丁堡大学信息学院） ； Southeast University, Nanjing, Jiangsu, China（东南大学） ； University of Manchester, UK（曼彻斯特大学） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.CL

Ai2 Scholar QA: Organized Literature Synthesis with Attribution

Amanpreet Singh, Joseph Chee Chang, Chloe Anastasiades, Dany Haddad, Aakanksha Naik, Amber Tanaka, Angele Zamarron, Cecile Nguyen, Jena D. Hwang, Jason Dunkleberger, Matt Latzke, Smita Rao, Jaron Lochner, Rob Evans, Rodney Kinney, Daniel S. Weld, Doug Downey, Sergey Feldman

机构 * Allen Institute for AI（Allen人工智能研究所） 纠错

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.CL

Comments 7 pages

Journal ref ACL 2025 System Demonstrations pages 513-523 Vienna Austria

ShadowCode: Towards (Automatic) External Prompt Injection Attack against Code LLMs

Yuchen Yang, Yiming Li, Hongwei Yao, Bingrun Yang, Yiling He, Tianwei Zhang, Dacheng Tao, Zhan Qin

机构 * State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学） ； Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security, Hangzhou（杭州高新区（滨江）区块链与数据安全研究院，杭州） ； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.AI

Enhancing Food-Domain Question Answering with a Multimodal Knowledge Graph: Hybrid QA Generation and Diversity Analysis

Srihari K B, Pushpak Bhattacharyya

专题命中 知识库问答 ：hybrid retrieval(abstract)；分类 cs.CL

Question Answering under Temporal Conflict: Evaluating and Organizing Evolving Knowledge with LLMs

Atahan Özer, Çağatay Yıldız

机构 * University of Tübingen（图宾根大学） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning

Qingfei Zhao, Ruobing Wang, Dingling Xu, Daren Zha, Limin Liu

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； Beijing Normal University（北京师范大学） 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

Comments 16 pages, 3 figures

Inter-Passage Verification for Multi-evidence Multi-answer QA

Bingsen Chen, Shengjie Wang, Xi Ye, Chen Zhao

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.CL

Comments 19 pages, 6 figures, to appear in ACL 2025 Findings

Exploring the Impact of Occupational Personas on Domain-Specific QA

Eojin Kang, Jaehyuk Yu, Juae Kim

专题命中 知识库问答 ：knowledge retrieval(abstract)；分类 cs.CL

Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA

Rishabh Maheshwary, Masoud Hashemi, Khyati Mahajan, Shiva Krishna Reddy Malay, Sai Rajeswar, Sathwik Tejaswi Madhusudhan, Spandana Gella, Vikas Yadav

机构 * ServiceNow 纠错

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation

Xiangci Li, Linfeng Song, Lifeng Jin, Haitao Mi, Jessica Ouyang, Dong Yu

专题命中 知识库问答 ：knowledge retrieval(abstract)；分类 cs.CL

Comments Accepted by LREC-COLING 2024

Journal ref https://aclanthology.org/2024.lrec-main.58/

MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering

Sofian Chaybouti, Achraf Saghe, Aymen Shabou

专题命中 知识库问答 ：retriever(abstract)；分类 cs.CL

Comments 8 pages, 7 figures, 3 tables

Towards Fine-Grained Video Question Answering

Wei Dai, Alan Luo, Zane Durante, Debadutta Dash, Arnold Milstein, Kevin Schulman, Ehsan Adeli, Li Fei-Fei

专题命中 知识库问答 ：retriever(abstract)；分类 cs.AI

KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA

Xiaorui Su, Yibo Wang, Shanghua Gao, Xiaolong Liu, Valentina Giunchiglia, Djork-Arné Clevert, Marinka Zitnik

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.AI

Journal ref ICLR2025

Open-Ended and Knowledge-Intensive Video Question Answering

Md Zarif Ul Alam, Hamed Zamani

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.IR

DeepThink: Aligning Language Models with Domain-Specific User Intents

Yang Li, Mingxuan Luo, Yeyun Gong, Chen Lin, Jian Jiao, Yi Liu, Kaili Huang

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

Finnish SQuAD: A Simple Approach to Machine Translation of Span Annotations

Emil Nuutinen, Iiro Rastas, Filip Ginter

专题命中 知识库问答 ：retriever(abstract)；分类 cs.CL

Comments NoDaLiDa 2025

Review-Then-Refine: A Dynamic Framework for Multi-Hop Question Answering with Temporal Adaptability

Xiangsen Chen, Xuming Hu, Nan Tang

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

Comments 20 pages, 2 figures

News Reporter: A Multi-lingual LLM Framework for Broadcast T.V News

Tarun Jain, Yufei Gao, Sridhar Vanga, Karan Singla

专题命中 知识库问答 ：RAG(abstract)；分类 cs.CL

Comments 5 pages, under review at ICASSP 2025

CompAct: Compressing Retrieved Documents Actively for Question Answering

Chanwoong Yoon, Taewhoo Lee, Hyeon Hwang, Minbyul Jeong, Jaewoo Kang

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；分类 cs.CL

Comments Accepted to the main conference at EMNLP 2024