RAG / 检索增强生成

CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos

Shengyao Zhuang, Guido Zuccon

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

Comments 9 pages full paper, accepted at SIGIR2022

LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback

Yunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng

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

Comments Accepted at SIGIR 2022

Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues

Gustavo Penha, Claudia Hauff

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

Synthetic Target Domain Supervision for Open Retrieval QA

Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan, Rong Zhang, Avirup Sil, Vittorio Castelli, Radu Florian, Salim Roukos

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

Comments Published at SIGIR 2021

TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge

Chao-Hong Tan, Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu, Huang Hu, Xiubo Geng, Daxin Jiang

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

Comments Accepted by Findings of ACL 2022

ReACC: A Retrieval-Augmented Code Completion Framework

Shuai Lu, Nan Duan, Hojae Han, Daya Guo, Seung-won Hwang, Alexey Svyatkovskiy

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

Comments Published in ACL 2022

RetGen: A Joint framework for Retrieval and Grounded Text Generation Modeling

Yizhe Zhang, Siqi Sun, Xiang Gao, Yuwei Fang, Chris Brockett, Michel Galley, Jianfeng Gao, Bill Dolan

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

Comments accepted by AAAI-22, camera ready version

Addressing Issues of Cross-Linguality in Open-Retrieval Question Answering Systems For Emergent Domains

Alon Albalak, Sharon Levy, William Yang Wang

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

Comments 6 pages, 8 figures

Improving Biomedical Information Retrieval with Neural Retrievers

Man Luo, Arindam Mitra, Tejas Gokhale, Chitta Baral

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

Comments Accepted at AAAI 2022

Multi Document Reading Comprehension

Avi Chawla

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

Comments 10 pages, 6 Figures

Establishing Strong Baselines for TripClick Health Retrieval

Sebastian Hofstätter, Sophia Althammer, Mete Sertkan, Allan Hanbury

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

Comments Accepted at ECIR 2022

Hindsight: Posterior-guided training of retrievers for improved open-ended generation

Ashwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia, Christopher D. Manning

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

Phrase Retrieval Learns Passage Retrieval, Too

Jinhyuk Lee, Alexander Wettig, Danqi Chen

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

Comments EMNLP 2021. Code available at https://github.com/princeton-nlp/DensePhrases

On Single and Multiple Representations in Dense Passage Retrieval

Craig Macdonald, Nicola Tonellotto, Iadh Ounis

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

Comments Published at the 11th Italian Information Retrieval Workshop (IIR 2021)

Pretrained Transformers for Text Ranking: BERT and Beyond

Jimmy Lin, Rodrigo Nogueira, Andrew Yates

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

Comments Final preproduction version of volume in Synthesis Lectures on Human Language Technologies by Morgan & Claypool

Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval

Luyu Gao, Jamie Callan

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

Cheap and Good? Simple and Effective Data Augmentation for Low Resource Machine Reading

Hoang Van, Vikas Yadav, Mihai Surdeanu

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

Comments 5 pages, 1 figure, SIGIR 2021

Neural Machine Translation with Monolingual Translation Memory

Deng Cai, Yan Wang, Huayang Li, Wai Lam, Lemao Liu

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

Comments ACL2021

Retrieval Enhanced Model for Commonsense Generation

Han Wang, Yang Liu, Chenguang Zhu, Linjun Shou, Ming Gong, Yichong Xu, Michael Zeng

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

Comments Findings of ACL-IJCNLP 2021

Improving Commonsense Question Answering by Graph-based Iterative Retrieval over Multiple Knowledge Sources

Qianglong Chen, Feng Ji, Haiqing Chen, Yin Zhang

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

Comments Accepted at COLING 2020

CMT in TREC-COVID Round 2: Mitigating the Generalization Gaps from Web to Special Domain Search

Chenyan Xiong, Zhenghao Liu, Si Sun, Zhuyun Dai, Kaitao Zhang, Shi Yu, Zhiyuan Liu, Hoifung Poon, Jianfeng Gao, Paul Bennett

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

Comments 5 pages, 3 figures, 2 tables

Open-Retrieval Conversational Question Answering

Chen Qu, Liu Yang, Cen Chen, Minghui Qiu, W. Bruce Croft, Mohit Iyyer

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

Comments Accepted to SIGIR'20

InjecMEM: Memory Injection Attack on LLM Agent Memory Systems

InjecMEM：针对大语言模型智能体记忆系统的内存注入攻击

Hanling Tian, Gengyu Zhang, Zeyang Sha, Jingying Wang, Yuhang Liu, Zhehao Huang, Kun Yang, Xiaolin Huang

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

AI总结 本研究提出InjecMEM内存注入攻击，无需访问LLM智能体内存存储，通过特定锚点与对抗性命令引导后续查询输出，在多模型上验证了其有效性，为智能体内存安全研究提供了可复现框架。

Comments 29 pages, 3 figures. Accepted at COLM 2026

Which Histories Matter for Time Series Forecasting? Learning Predictive Relevance with Future Supervision

时间序列预测中哪些历史数据重要？通过未来监督学习预测相关性

Yong-Hoon Choi, Youngjin Cho

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

AI总结 该研究针对时间序列预测的历史检索问题，提出基于未来监督的预测相关性重排序方法，在多基准任务中优于SARAF等检索规则，揭示历史相关性具结构化和领域依赖性。

Toward Effective and Reliable LLM Agents via Dynamic Ontology

基于动态本体的有效可靠大语言模型智能体研究

Xiaohui Zhang, Zequn Sun, Chengyuan Yang, Yuanning Cui, Lingbing Guo, Wei Hu

专题命中 检索器与排序 ：knowledge retrieval(abstract)；分类 cs.AI

AI总结 本文提出OaK框架，通过动态构建优化面向任务的本体论，在TravelPlanner等数据集上验证其可提升LLM智能体的证据基础与多步推理可靠性。

Risk-Aware Reranking for Agentic Tool Retrieval

面向智能体工具检索的风险感知重排序

Qinfei Li, Xiaoxuan Dong, Jin Zhang, Dexu Yu, Wenhao Deng, Junchen Fu, Youhua Li, Hanwen Du, Chunxiao Li

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

AI总结 本文针对智能体工具检索的风险问题，提出轻量级风险感知重排序框架，通过权衡安全与效用改善相关性-安全 tradeoff，为安全关键部署提供保守操作点。

Comments Accepted by CIKM 2026

Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical Prediction

采用开源权重大语言模型的角色专业化智能体混合架构用于临床预测

Jun Hou, Yi Fang, Xuan Wang

机构 * Virginia Tech（弗吉尼亚理工大学） 纠错

专题命中 检索器与排序 ：knowledge retrieval(abstract)；分类 cs.AI

AI总结 该研究提出角色专业化的开源权重智能体混合架构，结合医学知识检索与相似患者推理，在死亡率预测上媲美闭源模型且标记更多高危患者，为隐私约束下的临床LLM预测提供关键角色设计思路。

Comments COLM 2026 DAIH Workshop

Utility Under Attack: Agent Memory Poisoning and the Limits of Content Screening and Provenance Ranking

受攻击下的效用：智能体记忆投毒及内容筛选与来源排序的局限性

Arulnidhi Karunanidhi

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

AI总结 该研究针对智能体记忆投毒问题，测试了内容筛选和来源排序的防御效果，发现仅内容筛选无法抵御投毒，来源加权检索也存在局限，主张采用有限占用约束并发布了相关资源。

Projecting BrowseComp-Plus onto ClimbMix: Toward More Realistic Corpora for Agentic Search

将BrowseComp-Plus映射到ClimbMix：构建更符合智能体搜索需求的真实语料库

Sahel Sharifymoghaddam, Lingwei Gu, Yijun Ge, Jimmy Lin

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

AI总结 该研究将BrowseComp-Plus的查询映射到NVIDIA的ClimbMix语料库，构建了与基准无关的映射流水线，生成57个有效查询，使智能体搜索难度向检索环节转移，发布了相关资源。

The First Drop of Ink: Nonlinear Impact of Distracting Information in Long-Context Reasoning

第一滴墨水：误导信息在长上下文推理中的非线性影响

Muhan Gao, Zih-Ching Chen, Kuan-Hao Huang

机构 * Department of Computer Science ； Engineering, Texas A\&M University, College Station, TX, USA ； NVIDIA AI Technology Center, NVIDIA Corporation, Santa Clara, CA, USA 纠错

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

AI总结 研究探讨了误导信息在长上下文推理中的非线性影响，发现误导信息比例增加时，性能在初期急剧下降，后续变化较小。通过理论和实证分析，揭示了误导信息对注意力的 disproportionate 影响，并指出过滤收益主要来自减少上下文长度而非去除误导信息。