RAG / 检索增强生成

Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context

基于引用的代码理解：通过混合检索和图增强上下文防止LLM幻觉

Jahidul Arafat

机构 * Department of Computer Science and Software Engineering, Auburn University, Alabama, USA（计算机科学与软件工程系，阿伯丁大学，阿拉巴马州，美国） 纠错

专题命中 检索器与排序 ：hybrid retrieval(title,abstract)

AI总结 本文提出混合检索与图增强上下文方法，通过系统评估实现92%引用准确率，有效防止LLM幻觉。

Hierarchical Deep Research with Local-Web RAG: Toward Automated System-Level Materials Discovery

分层深度研究与本地Web RAG：迈向自动化系统级材料发现

Rui Ding, Rodrigo Pires Ferreira, Yuxin Chen, Junhong Chen

机构 * Pritzker School of Molecular Engineering, University of Chicago（芝加哥大学普利兹克分子工程学院） ； Chemical Sciences and Engineering Division, Argonne National Laboratory（阿贡国家实验室化学科学与工程 division） ； Department of Computer Science, University of Chicago（芝加哥大学计算机科学系） 纠错

专题命中 检索器与排序 ：RAG(title)；retrieval-augmented generation(abstract)

AI总结 本文提出一种分层深度研究代理，通过本地Web RAG和DToR机制，实现低成本高质的自动化系统级材料发现。

Comments A preliminary version appeared in The AI for Accelerated Materials Discovery (AI4Mat) Workshop at NeurIPS 2025

Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation

Ziyu Liu, Yijing Liu, Jianfei Yuan, Minzhi Yan, Le Yue, Honghui Xiong, Yi Yang

机构 * Huawei Cloud Computing Technology Co., Ltd, China（华为云计算技术有限公司，中国） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title)；RAG(abstract)

CardioRAG: A Retrieval-Augmented Generation Framework for Multimodal Chagas Disease Detection

Zhengyang Shen, Xuehao Zhai, Hua Tu, Mayue Shi

机构 * Department of Electrical and Electronic Engineering Imperial College London（帝国理工学院电子与电气工程系） ； Department of Civil and Environmental Engineering Imperial College London（帝国理工学院土木与环境工程系） ； Institute of Biomedical Engineering Department of Engineering Science University of Oxford（牛津大学生物医学工程研究所） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)

Comments 4 pages, 2 figures. Accepted for oral presentation at the 52nd international Computing in Cardiology Conference (CinC2025)

LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration

Yukun Cao, Zengyi Gao, Zhiyang Li, Xike Xie, S. Kevin Zhou, Jianliang Xu

机构 * University of Science and Technology of China（中国科学技术大学） ； Hong Kong Baptist University（香港 Baptist 大学） 纠错

专题命中 检索器与排序 ：retrieval-augmented generation(title)；分类 cs.CL、cs.AI、cs.DB

Comments VLDB'2025 [Experiment, Analysis & Benchmark]

Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning

Runzhong Wang, Rui-Xi Wang, Mrunali Manjrekar, Connor W. Coley

机构 * Massachusetts Institute of Technology, Cambridge, MA, United States（麻省理工学院） 纠错

专题命中 检索器与排序 ：retrieval augmented generation(title)；retrieval-augmented generation(abstract)

Comments ICML 2025

GD-Retriever: Controllable Generative Text-Music Retrieval with Diffusion Models

Julien Guinot, Elio Quinton, György Fazekas

专题命中 检索器与排序 ：retriever(title,abstract)

Comments Accepted to ISMIR 2025

RAG-6DPose: Retrieval-Augmented 6D Pose Estimation via Leveraging CAD as Knowledge Base

Kuanning Wang, Yuqian Fu, Tianyu Wang, Yanwei Fu, Longfei Liang, Yu-Gang Jiang, Xiangyang Xue

机构 * Fudan University（复旦大学） ； NeuhHelium Co.,Ltd.（NeuhHelium公司） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)

Comments Accepted by IROS 2025

MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents

Junpeng Yue, Xinrun Xu, Börje F. Karlsson, Zongqing Lu

机构 * School of Computer Science, Peking University（北京大学计算机科学学院） ； Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所） ； Beijing Academy of Artificial Intelligence（北京人工智能研究院） 纠错

专题命中 检索器与排序 ：retriever(title,abstract)

Comments ICLR 2025

MANTRA: Enhancing Automated Method-Level Refactoring with Contextual RAG and Multi-Agent LLM Collaboration

Yisen Xu, Feng Lin, Jinqiu Yang, Tse-Hsun, Chen, Nikolaos Tsantalis

专题命中 检索器与排序 ：RAG(title)；retrieval-augmented generation(abstract)

Comments 10 pages

Instructive Code Retriever: Learn from Large Language Model's Feedback for Code Intelligence Tasks

Jiawei Lu, Haoye Wang, Zhongxin Liu, Keyu Liang, Lingfeng Bao, Xiaohu Yang

专题命中 检索器与排序 ：retriever(title,abstract)

Comments to appear at the 39th IEEE/ACM International Conference on Automated Software Engineering (ASE 2024)

MultiContrievers: Analysis of Dense Retrieval Representations

Seraphina Goldfarb-Tarrant, Pedro Rodriguez, Jane Dwivedi-Yu, Patrick Lewis

专题命中 检索器与排序 ：dense retrieval(title)；分类 cs.IR、cs.CL、cs.AI

RAG-Enhanced Commit Message Generation

Linghao Zhang, Hongyi Zhang, Chong Wang, Peng Liang

专题命中 检索器与排序 ：RAG(title)；retriever(abstract)

Comments 22 pages, 5 images, 6 tables, Manuscript submitted to a journal (2024)

A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks

Nicholas Monath, Will Grathwohl, Michael Boratko, Rob Fergus, Andrew McCallum, Manzil Zaheer

专题命中 检索器与排序 ：retriever(title)；dense retrieval(abstract)

Comments ICML 2024

Generative Language Models with Retrieval Augmented Generation for Automated Short Answer Scoring

Zifan Wang, Christopher Ormerod

专题命中 检索器与排序 ：retrieval augmented generation(title)；分类 cs.IR、cs.CL、cs.AI

Comments 20 pages, 2 figures

LAKE-RED: Camouflaged Images Generation by Latent Background Knowledge Retrieval-Augmented Diffusion

Pancheng Zhao, Peng Xu, Pengda Qin, Deng-Ping Fan, Zhicheng Zhang, Guoli Jia, Bowen Zhou, Jufeng Yang

专题命中 检索器与排序 ：knowledge retrieval(title,abstract)

Comments Accepted by CVPR 2024, Fig.2 and Equation 4 revised

Optimization of Retrieval-Augmented Generation Context with Outlier Detection

Vitaly Bulgakov

专题命中 检索器与排序 ：retrieval-augmented generation(title)；分类 cs.IR、cs.CL、cs.AI

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Andreas Koukounas, Georgios Mastrapas, Michael Günther, Bo Wang, Scott Martens, Isabelle Mohr, Saba Sturua, Mohammad Kalim Akram, Joan Fontanals Martínez, Saahil Ognawala, Susana Guzman, Maximilian Werk, Nan Wang, Han Xiao

专题命中 检索器与排序 ：retriever(title)；分类 cs.IR、cs.CL、cs.AI

Comments 4 pages, MFM-EAI@ICML2024

Dynamic Retrieval-Augmented Generation

Anton Shapkin, Denis Litvinov, Yaroslav Zharov, Egor Bogomolov, Timur Galimzyanov, Timofey Bryksin

专题命中 检索器与排序 ：retrieval-augmented generation(title,abstract)

Comments 10 pages

Extracting task trees using knowledge retrieval search algorithms in functional object-oriented network

Tyree Lewis

专题命中 检索器与排序 ：knowledge retrieval(title,abstract)

Comments 5 pages, 8 figures, 8 tables

Noise-Robust Dense Retrieval via Contrastive Alignment Post Training

Daniel Campos, ChengXiang Zhai, Alessandro Magnani

专题命中 检索器与排序 ：dense retrieval(title)；分类 cs.IR、cs.CL、cs.AI

Comments 8 pages, 6 figures, 30 tables

Context Recovery and Knowledge Retrieval: A Novel Two-Stream Framework for Video Anomaly Detection

Congqi Cao, Yue Lu, Yanning Zhang

专题命中 检索器与排序 ：knowledge retrieval(title,abstract)

Comments 13 pages, 10 figures

HyDRA-H: Simultaneous Hybrid Retrieval of Exoplanetary Emission Spectra

Siddharth Gandhi, Nikku Madhusudhan, George Hawker, Anjali Piette

专题命中 检索器与排序 ：hybrid retrieval(title,abstract)

Comments 16 pages, 9 figures, accepted for publication in The Astronomical Journal

Hybrid Retrieval-Generation Reinforced Agent for Medical Image Report Generation

Christy Y. Li, Xiaodan Liang, Zhiting Hu, Eric P. Xing

专题命中 检索器与排序 ：hybrid retrieval(title,abstract)

Skill Is Not Document: Query-Conditioned Compatibility for LLM Agent Skill Routing

技能不是文档：面向LLM智能体技能路由的查询条件基准与两阶段检索器

Zifei Wang, Wei Wen, Qiang Ji, Keyu Chen, Ruizhi Qiao, Xing Sun

专题命中 检索器与排序 ：retriever(summary_cn,abstract_cn)；分类 cs.IR

AI总结 针对LLM智能体技能路由中技能兼容性被忽视的问题，提出Reject-as-Resource Retriever (R3)框架，构建双语基准R3-Skill，并设计两阶段检索系统（R3-Embedding + R3-Reranker）显式建模技能兼容性，显著提升检索效果。

Comments 24 pages, 8 figures

TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion

TFGformer：基于时频图学习与协变量融合的多变量时间序列预测

Yu Sun, Yuan Chang, Xiaohou Shi, Yan Sun

专题命中 检索器与排序 ：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)；分类 cs.AI

AI总结 针对异构IoT传感器多变量时间序列预测问题，提出CrossRAG框架，结合SAM、FCC学习与CATF，在7个基准上性能优于仅参数化基线及现有检索增强预测方法。

What Softmax Throws Away: Mass-Aware Attention for Evidence Accumulation

Softmax丢弃的信息：用于证据积累的质量感知注意力

Minwoo Yu, Young-guk Ha

机构 * Smart Computing Laboratory, Department of Computer Science & Engineering, Konkuk University（智能计算实验室，计算机科学与工程系，建国大学） 纠错

专题命中 检索器与排序 ：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)；分类 cs.AI

AI总结 研究探讨模型内部表示中预测相关结构信息保留问题，提出质量感知注意力（MAA），将标准L1归一化推广到Lp族，在多模型和数据集上提升未来链接AUC等，定位为通用归一化原则提高表示信息性。

Procedural Knowledge at Scale Improves Reasoning

大规模程序知识提升推理能力

Di Wu, Devendra Singh Sachan, Wen-tau Yih, Mingda Chen

机构 * University of California, Los Angeles（加州大学洛杉矶分校） ； Meta FAIR 纠错

专题命中 检索器与排序 ：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结 本研究提出Reasoning Memory框架，通过大规模检索增强生成方法，有效利用程序知识提升推理能力，在多个基准测试中表现优于现有方法。

Comments COLM 2026 Camera Ready

Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models

通过检索增强大语言模型利用外部知识进行历史文献修复

Gabeen Kim, Kyeongpil Kang

机构 * Kangwon National University（江原国立大学） 纠错

专题命中 检索器与排序 ：RAG(abstract,abstract_cn)；retrieval-augmented generation(abstract)；分类 cs.CL

AI总结 针对历史文献因物理损坏难以辨认及现有修复方法在恢复命名实体上的局限，提出利用检索增强大语言模型的修复框架，结合预训练模型隐含知识与外部上下文，实验表明该方法性能优于基线，是历史记录分析实用工具。

Comments Accepted to Findings of ACL 2026

Journal ref Findings of the Association for Computational Linguistics: ACL 2026, pages 43290-43304, 2026

Enhancing SLMs for Sustainable Code Optimization in Radio-Astronomy

增强小型语言模型以实现射电天文学中的可持续代码优化

Elisa Chiarotto, Jingbo Li, P. Chris Broekema, Rob V. van Nieuwpoort

专题命中 检索器与排序 ：RAG(abstract,abstract_cn)；retrieval augmented generation(abstract)；分类 cs.AI

AI总结 研究利用小型语言模型（SLMs）优化射电天文学代码，通过多采样生成策略和纳入编译器反馈两种方式增强SLMs，提高代码生成质量和性能，用更少计算资源匹配或超越大型单生成模型，且使所有测试模型持续改进。