RAG / 检索增强生成

Optimizing Test-Time Query Representations for Dense Retrieval

Mujeen Sung, Jungsoo Park, Jaewoo Kang, Danqi Chen, Jinhyuk Lee

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

Comments Findings of ACL 2023

What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary

Ori Ram, Liat Bezalel, Adi Zicher, Yonatan Belinkov, Jonathan Berant, Amir Globerson

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

Comments ACL 2023

BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval

Shicheng Xu, Liang Pang, Huawei Shen, Xueqi Cheng

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

Comments Accepted by ACL 2023 Main

ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval

Yue Yu, Yuchen Zhuang, Rongzhi Zhang, Yu Meng, Jiaming Shen, Chao Zhang

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

Comments ACL 2023 Findings (Code: https://github.com/yueyu1030/ReGen)

A Thorough Examination on Zero-shot Dense Retrieval

Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, Qifei Wu, Yuchen Ding, Hua Wu, Haifeng Wang, Ji-Rong Wen

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

Questions Are All You Need to Train a Dense Passage Retriever

Devendra Singh Sachan, Mike Lewis, Dani Yogatama, Luke Zettlemoyer, Joelle Pineau, Manzil Zaheer

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

Comments Accepted to TACL, pre MIT Press publication version

Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters

Eugene Yang, Suraj Nair, Dawn Lawrie, James Mayfield, Douglas W. Oard

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

Comments 15 pages, 1 figure

Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models

Shujian Zhang, Chengyue Gong, Xingchao Liu

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

Comments EMNLP 2022

Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval

Jingtao Zhan, Qingyao Ai, Yiqun Liu, Jiaxin Mao, Xiaohui Xie, Min Zhang, Shaoping Ma

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

Comments Preprint

Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval

Zehan Li, Nan Yang, Liang Wang, Furu Wei

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

Are We There Yet? A Decision Framework for Replacing Term Based Retrieval with Dense Retrieval Systems

Sebastian Hofstätter, Nick Craswell, Bhaskar Mitra, Hamed Zamani, Allan Hanbury

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

Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training

Yifan Gao, Qingyu Yin, Zheng Li, Rui Meng, Tong Zhao, Bing Yin, Irwin King, Michael R. Lyu

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

Comments NAACL 2022 (Findings)

Neural Retriever and Go Beyond: A Thesis Proposal

Man Luo

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

Comments Accepted to NAACL 2022 SRW

GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval

Kexin Wang, Nandan Thakur, Nils Reimers, Iryna Gurevych

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

Comments Accepted at NAACL 2022

Exploring Dense Retrieval for Dialogue Response Selection

Tian Lan, Deng Cai, Yan Wang, Yixuan Su, Heyan Huang, Xian-Ling Mao

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

Comments 11 pages, 4 figures, 6 tables

Towards Best Practices for Training Multilingual Dense Retrieval Models

Xinyu Zhang, Kelechi Ogueji, Xueguang Ma, Jimmy Lin

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

Multi-View Document Representation Learning for Open-Domain Dense Retrieval

Shunyu Zhang, Yaobo Liang, Ming Gong, Daxin Jiang, Nan Duan

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

Comments ACL 2022

Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong C. Park

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

Comments ACL 2022

Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search

Jianjin Zhang, Zheng Liu, Weihao Han, Shitao Xiao, Ruicheng Zheng, Yingxia Shao, Hao Sun, Hanqing Zhu, Premkumar Srinivasan, Denvy Deng, Qi Zhang, Xing Xie

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

Transfer Learning Approaches for Building Cross-Language Dense Retrieval Models

Suraj Nair, Eugene Yang, Dawn Lawrie, Kevin Duh, Paul McNamee, Kenton Murray, James Mayfield, Douglas W. Oard

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

Comments Accepted at ECIR 2022 (Full paper)

Boosted Dense Retriever

Patrick Lewis, Barlas Oğuz, Wenhan Xiong, Fabio Petroni, Wen-tau Yih, Sebastian Riedel

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

Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval

Xinyu Zhang, Xueguang Ma, Peng Shi, Jimmy Lin

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

Comments Workshop on Multilingual Representation Learning at EMNLP 2021

Cross-Lingual Training with Dense Retrieval for Document Retrieval

Peng Shi, Rui Zhang, He Bai, Jimmy Lin

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

Visual RAG Toolkit: Scaling Multi-Vector Visual Retrieval with Training-Free Pooling and Multi-Stage Search

视觉RAG工具包：通过无训练池化和多阶段搜索扩展多向量视觉检索

Ara Yeroyan

机构 * Independent Researcher（独立研究者） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；分类 cs.IR

AI总结 视觉RAG工具包通过无训练池化和多阶段搜索提升多向量视觉检索效率，减少向量存储并提高检索吞吐量。

Comments 4 pages, 3 figures. Submitted to SIGIR 2026 Demonstrations Track. Project website: https://github.com/Ara-Yeroyan/visual-rag-toolkit

Domain-Adaptive and Scalable Dense Retrieval for Content-Based Recommendation

面向领域适应和可扩展的密集检索用于基于内容的推荐

Mritunjay Pandey

机构 * Aditya Birla Group（阿迪提亚·布尔拉集团） 纠错

专题命中 检索器与排序 ：dense retrieval(title,abstract)；分类 cs.IR

AI总结 本文提出了一种基于双塔双编码器的可扩展密集检索系统，通过领域适应提升基于内容的推荐效果，实现高效服务和模型压缩。

Comments 13 pages, 4 figures. Semantic dense retrieval for content-based recommendation on Amazon Reviews 2023 (Category - Fashion). Dataset statistics: 2.0M users; 825.9K items; 2.5M ratings; 94.9M review tokens; 510.5M metadata tokens. Timespan: May 1996 to September 2023. Metadata includes: user reviews (ratings, text, helpfulness votes, etc.); item metadata (descriptions, price, raw images, etc.)

MV-RAG: Retrieval Augmented Multiview Diffusion

Yosef Dayani, Omer Benishu, Sagie Benaim

机构 * Hebrew University of Jerusalem（耶路撒冷希伯来大学） 纠错

专题命中 检索器与排序 ：RAG(title,abstract)；分类 cs.AI

Comments Project page: https://yosefdayani.github.io/MV-RAG

Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph

Dacheng Yin, Xuanchi Ren, Chong Luo, Yuwang Wang, Zhiwei Xiong, Wenjun Zeng

专题命中 检索器与排序 ：retriever(title,abstract)；分类 cs.AI

Comments Accepted to ICLR 2022. Project page at https://ydcustc.github.io/retriever-demo/

Knowledge-Graph-Guided Retrieval-Augmented LLMs for Explainable Root Cause Analysis in Automotive HiL Validation

知识图谱引导的检索增强大语言模型用于汽车在环（HiL）验证中的可解释根本原因分析

Hamza Ouarrad, Mohammad Abboush, Andreas Rausch

专题命中 检索器与排序 ：RAG(summary_cn,abstract)

AI总结 该研究提出KG引导的RAG-LLM框架，用于汽车HiL数据的RCA与故障定位，在ASM汽油发动机和电动车系统案例中分别获90%、94% Top-1准确率，可实现可解释且泛化的故障分析。

Comments 10 pages, 3 figures, 5 tables. Accepted for publication and oral presentation at the 10th International Conference on System Reliability and Safety (ICSRS 2026), Rome, Italy, November 23--25, 2026

Multimodal CoLRAG-TF: Triple-Filtered Retrieval for Complex PDFs

多模态CoLRAG-TF：复杂PDF的三重过滤检索

Takato Yasuno

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

AI总结 研究针对异构PDF集合检索增强生成的挑战，提出多模态CoLRAG-TF四轴融合架构，集成多种技术。构建多模态索引，经贝叶斯优化确定融合权重。实验显示其检索召回率高，多跳答案相似性提升显著，还适用于视觉输入，提供通用框架。

Comments 18 pages, 8 tables, 9 figures

Fidelity Before Structure: Verbatim Chunks Beat Lossy Artifact Extraction in Long-Conversation LLM Memory

逐字块胜过提取的人工制品：长LLM对话中记忆表征的控制消融研究

Tao An

机构 * Hawaii Pacific University（夏威夷太平洋大学） 纠错

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

AI总结 通过控制消融实验，发现逐字对话块在长对话记忆检索中比LLM提取的结构化人工制品（事实、决策等）准确率高15.9-22.0点，原因是提取过程丢失了逐字细节，而结构化记忆应作为逐字文本的补充而非替代。

Comments v4: title and abstract aligned with ARR August 2026 submission; six confound controls; 34 pages, 6 figures. Code: https://github.com/tao-hpu/cog-canvas