RAG / 检索增强生成

Pragya: An AI-Based Semantic Recommendation System for Sanskrit Subhasitas

Pragya：一种基于人工智能的印地语Subhasitas语义推荐系统

Tanisha Raorane, Prasenjit Kole

机构 * Department of Computer Engineering Don Bosco Institute of Technology Mumbai, India（计算机工程系 内华大学技术学院 孟买 印度） ； Department of Mechanical Engineering Don Bosco Institute of Technology Mumbai, India（机械工程系 内华大学技术学院 孟买 印度） 纠错

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

AI总结 Pragya通过结合检索与生成技术，为印地语Subhasitas提供语义推荐，提升其在数字时代的可访问性和应用价值。

Comments Preprint

CliCARE: Grounding Large Language Models in Clinical Guidelines for Decision Support over Longitudinal Cancer Electronic Health Records

CliCARE: 在纵向癌症电子健康记录上基于临床指南 grounding 大型语言模型以支持决策

Dongchen Li, Jitao Liang, Wei Li, Xiaoyu Wang, Longbing Cao, Kun Yu

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

AI总结 CliCARE 通过将纵向癌症 EHRs 转换为时序知识图谱并结合临床指南，为肿瘤科医生提供证据支持的决策支持。

Comments Accepted in AAAI Conference on Artificial Intelligence (AAAI-26, Oral)

The Instruction Gap: LLMs get lost in Following Instruction

指令鸿沟：LLMs在遵循指令时迷失

Vishesh Tripathi, Uday Allu, Biddwan Ahmed

机构 * Vishesh Tripathi ； Uday Allu ； Biddwan Ahmed 纠错

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

AI总结 本研究揭示了LLMs在企业部署中遵循指令的不足，通过评估13种模型发现Claude-Sonnet-4和GPT-5表现最佳，指出指令遵循能力的鸿沟及改进方向。

Hallucination to Truth: A Review of Fact-Checking and Factuality Evaluation in Large Language Models

幻觉与事实：大型语言模型中事实核查与事实性评估的综述

Subhey Sadi Rahman, Md. Adnanul Islam, Md. Mahbub Alam, Musarrat Zeba, Md. Abdur Rahman, Sadia Sultana Chowa, Mohaimenul Azam Khan Raiaan, Sami Azam

机构 * Department of Computer Science and Engineering, United International University, Dhaka 1212, Bangladesh（乌姆特国际大学计算机科学与工程系） ； Department of Computer Science and Engineering, Daffodil International University, Dhaka-1341, Bangladesh（达芙尼国际大学计算机科学与工程系） ； Faculty of Science and Technology, Charles Darwin University, Casuarina, NT 0909, Australia（查尔斯·达尔文大学科学与技术学院） 纠错

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

AI总结 本文综述了大型语言模型中事实核查与事实性评估的关键挑战及方法，强调了提升事实准确性的重要性。

Journal ref Artif. Intell. Rev. (2026)

From Transformers to LLMs: A Systematic Survey of Efficiency Considerations in NLP

从Transformer到LLM：NLP中基于效率考虑的系统性综述

Wazib Ansar, Saptarsi Goswami, Amlan Chakrabarti

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

AI总结 本文系统综述了NLP中基于Transformer的LLM在效率方面的研究，探讨了数据整理、模型设计等多方面效率提升方法，并评估了多个知名NLP模型的效率和有效性。

Comments 63 pages, 5 tables and 22 figures

PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI

PrivacyBench: 一个用于评估个性化AI隐私的对话基准

Srija Mukhopadhyay, Sathwik Reddy, Shruthi Muthukumar, Jisun An, Ponnurangam Kumaraguru

机构 * International Institute of Information Technology Hyderabad（国际信息科技研究所（海得拉巴）） ； Indiana University（印第安纳大学） 纠错

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

AI总结 PrivacyBench通过多轮对话评估揭示RAG助手在隐私保护上的缺陷，指出需结构性隐私保障措施以确保伦理网络环境。

Comments 11 pages, 2 figures

MegaChat: A Synthetic Persian Q&A Dataset for High-Quality Sales Chatbot Evaluation

MegaChat: 一个用于高质量销售聊天机器人评估的合成波斯语问答数据集

Mahdi Rahmani, AmirHossein Saffari, Reyhane Rahmani

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

AI总结 MegaChat通过自动化多代理架构生成高质量波斯语问答数据，用于评估销售聊天机器人，优于传统RAG模型。

Comments 6 pages, 11 figures, 2 tables

Stemming Hallucination in Language Models Using a Licensing Oracle

Simeon Emanuilov, Richard Ackermann

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

Comments 23 pages, 4 figures, 8 tables. Introduces the Licensing Oracle, an architectural solution for eliminating hallucinations in language models through formal SHACL validation against knowledge graphs. All datasets and models are available at https://huggingface.co/collections/s-emanuilov/licensing-oracle-experiments

InsurAgent: A Large Language Model-Empowered Agent for Simulating Individual Behavior in Purchasing Flood Insurance

Ziheng Geng, Jiachen Liu, Ran Cao, Lu Cheng, Dan M. Frangopol, Minghui Cheng

机构 * University of Miami（迈阿密大学） ； Hunan University（湖南大学） ； University of Illinois Chicago（伊利诺伊大学香槟分校） ； Lehigh University（莱斯大学） 纠错

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

A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications

Minhua Lin, Zongyu Wu, Zhichao Xu, Hui Liu, Xianfeng Tang, Qi He, Charu Aggarwal, Hui Liu, Xiang Zhang, Suhang Wang

机构 * The Pennsylvania State University（宾夕法尼亚州立大学） ； The University of Utah（犹他大学） ； Amazon（亚马逊） ； Microsoft（微软） ； IBM T.J. Watson Research Center（IBM T.J.沃森研究中心） ； Michigan State University（密歇根州立大学） 纠错

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

Comments 38 pages, 4 figures, 7 tables

Redefining Retrieval Evaluation in the Era of LLMs

Giovanni Trappolini, Florin Cuconasu, Simone Filice, Yoelle Maarek, Fabrizio Silvestri

机构 * Sapienza University of Rome（萨皮恩扎罗马大学） ； Technology Innovation Institute（技术创新研究所） 纠错

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

MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?

Kai Yan, Zhan Ling, Kang Liu, Yifan Yang, Ting-Han Fan, Lingfeng Shen, Zhengyin Du, Jiecao Chen

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments 39 pages, 11 figures. The paper is accepted at NeurIPS 2025 Datasets & Benchmarks Track, and the latest version adds modifications in camera-ready

NAACL2025 Tutorial: Adaptation of Large Language Models

Zixuan Ke, Yifei Ming, Shafiq Joty

机构 * Salesforce AI Research（Salesforce人工智能研究） 纠错

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

Comments NAACL2025 Tutorial

Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs

Yehor Tereshchenko, Mika Hämäläinen

机构 * Metropolia University of Applied Sciences（Metropolia应用科学大学） 纠错

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

Comments Published in the Journal of Data Mining & Digital Humanities (JDMDH), special issue NLP4DH

Journal ref Journal of Data Mining & Digital Humanities, NLP4DH, October 14, 2025

Judge's Verdict: A Comprehensive Analysis of LLM Judge Capability Through Human Agreement

Steve Han, Gilberto Titericz Junior, Tom Balough, Wenfei Zhou

机构 * NVIDIA Corporation（NVIDIA公司） 纠错

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

Comments 10 pages, 1 figure, 4 tables, under review as a conference paper at ICLR 2026

AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents

Jiabin Tang, Tianyu Fan, Chao Huang

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

Comments Code: https://github.com/HKUDS/AutoAgent

Geolog-IA: Conversational System for Academic Theses

Micaela Fuel Pozo, Andrea Guatumillo Saltos, Yeseña Tipan Llumiquinga, Kelly Lascano Aguirre, Marilyn Castillo Jara, Christian Mejia-Escobar

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

Comments 17 pages, in Spanish language

Small Language Models for Curriculum-based Guidance

Konstantinos Katharakis, Sippo Rossi, Raghava Rao Mukkamala

机构 * Copenhagen Business School（哥本哈根商学院） ； Hanken School of Economics（汉肯经济学院） 纠错

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

Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey

Kolawole Tytler

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

LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology

Renan Souza, Timothy Poteet, Brian Etz, Daniel Rosendo, Amal Gueroudji, Woong Shin, Prasanna Balaprakash, Rafael Ferreira da Silva

机构 * Oak Ridge National Lab.（橡树岭国家实验室） ； Argonne National Lab.（阿贡国家实验室） 纠错

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

Comments Paper accepted in the proceedings of the Supercomputing Conference (SC). Cite it as Renan Souza, Timothy Poteet, Brian Etz, Daniel Rosendo, Amal Gueroudji, Woong Shin, Prasanna Balaprakash, and Rafael Ferreira da Silva. LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology. In WORKS at the ACM/IEEE International Conference on Supercomputing, 2025

Quality Assessment of Tabular Data using Large Language Models and Code Generation

Ashlesha Akella, Akshar Kaul, Krishnasuri Narayanam, Sameep Mehta

机构 * IBM Research（IBM研究院） 纠错

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

Comments under review

When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine

Lijia Ma, Juan Qin, Xingchen Xu, Yong Tan

机构 * Belk College of Business, University of North Carolina at Charlotte（北卡罗来纳州立大学查尔斯顿分校商学院） ； Faculty of Business for Science and Technology, School of Management, University of Science and Technology of China（中国科学技术大学管理学院科学技术商学院） ； Michael G. Foster School of Business, University of Washington（华盛顿大学Michael G. Foster商学院） 纠错

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

Comments 59 pages, 6 figures, 20 tables

Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion

Happymore Masoka

机构 * Pace University（帕克大学） ； Seidenberg School of Computer Science and Information Systems（塞登堡计算机科学与信息系统学院） 纠错

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

DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models

Xiao Zheng

机构 * School of Computing and Technology（计算机学院） ； China University of Petroleum（中国石油大学） ； Qingdao（青岛） 纠错

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

DentalBench: Benchmarking and Advancing LLMs Capability for Bilingual Dentistry Understanding

Hengchuan Zhu, Yihuan Xu, Yichen Li, Zijie Meng, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； ZJU-Angelalign R&D Center for Intelligence Healthcare（浙江大学智能医疗研发中心） 纠错

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

SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models

Tong Bao, Mir Tafseer Nayeem, Davood Rafiei, Chengzhi Zhang

机构 * Nanjing University of Science and Technology（南京理工大学） ； University of Alberta（阿尔伯塔大学） 纠错

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

Journal ref EMNLP2025

The illusion of a perfect metric: Why evaluating AI's words is harder than it looks

Maria Paz Oliva, Adriana Correia, Ivan Vankov, Viktor Botev

机构 * Iris AI Borgen, Norway（Iris AI 布尔根，挪威） ； Iris AI Neurobiology BAS Sofia, Bulgaria（Iris AI 神经生物学 BAS 萨福ia，保加利亚） ； Iris AI Sofia, Bulgaria（Iris AI 萨福ia，保加利亚） 纠错

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

Comments 11 pages, 1 figure. Accepted to RANLP 2025

WebWalker: Benchmarking LLMs in Web Traversal

Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, Fei Huang

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

ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings

Ali Shiraee Kasmaee, Mohammad Khodadad, Mehdi Astaraki, Mohammad Arshi Saloot, Nicholas Sherck, Hamidreza Mahyar, Soheila Samiee

机构 * Department of Computational Science and Engineering（计算科学与工程系） ； McMaster University（麦斯特大学） ； BASF Canada Inc（巴斯夫加拿大公司） ； BASF Corporation（巴斯夫公司） 纠错

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

ORANSight-2.0: Foundational LLMs for O-RAN

Pranshav Gajjar, Vijay K. Shah

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