RAG / 检索增强生成 - arXivDaily 专题

2110.02067 2021-10-06 cs.CL 57%

Teach Me What to Say and I Will Learn What to Pick: Unsupervised Knowledge Selection Through Response Generation with Pretrained Generative Models

Ehsan Lotfi, Maxime De Bruyn, Jeska Buhmann, Walter Daelemans

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

Comments Accepted at ConvAI workshop (EMNLP 2021)

2109.05487 2021-09-14 cs.CL 57%

Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

Leyang Cui, Yu Wu, Shujie Liu, Yue Zhang

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

Comments EMNLP 2021

2108.12139 2021-09-14 cs.IR 57%

Dealing with Typos for BERT-based Passage Retrieval and Ranking

Shengyao Zhuang, Guido Zuccon

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

Comments Short paper, accepted at EMNLP2021 main conference

2108.11601 2021-09-13 cs.SE cs.CL 57%

Retrieval Augmented Code Generation and Summarization

Md Rizwan Parvez, Wasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang

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

Comments accepted in EMNLP-Findings 2021

2108.00644 2021-08-24 cs.IR 57%

Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, Shaoping Ma

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

Comments Accepted by CIKM 2021 as a full paper

2108.03322 2021-08-10 cs.IR cs.LG cs.SE 57%

Distilling Transformers for Neural Cross-Domain Search

Colin B. Clement, Chen Wu, Dawn Drain, Neel Sundaresan

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

Comments 4 pages, 1 figure, emnlp formatting

2107.14740 2021-08-02 cs.CL 57%

Automatic Claim Review for Climate Science via Explanation Generation

Shraey Bhatia, Jey Han Lau, Timothy Baldwin

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

2107.05720 2021-07-14 cs.IR 57%

SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant

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

Comments 5 pages, SIGIR'21 short paper

2105.06041 2021-06-03 cs.CL 57%

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

Silin Gao, Ryuichi Takanobu, Wei Peng, Qun Liu, Minlie Huang

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

Comments Findings of ACL-IJCNLP 2021, long paper

2104.08710 2021-04-20 cs.CL 57%

Simple and Efficient ways to Improve REALM

Vidhisha Balachandran, Ashish Vaswani, Yulia Tsvetkov, Niki Parmar

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

2101.00117 2021-01-05 cs.CL 57%

Multi-task Retrieval for Knowledge-Intensive Tasks

Jean Maillard, Vladimir Karpukhin, Fabio Petroni, Wen-tau Yih, Barlas Oğuz, Veselin Stoyanov, Gargi Ghosh

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

2010.00840 2020-10-05 cs.CL 57%

MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models

Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Raul Puri, Pascale Fung, Anima Anandkumar, Bryan Catanzaro

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

Comments Accepted in EMNLP 2020 main conference

2009.06857 2020-09-16 cs.CL cs.LG 57%

Current Limitations of Language Models: What You Need is Retrieval

Aran Komatsuzaki

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

1807.02189 2020-08-03 cs.RO cs.AI 57%

Functional Object-Oriented Network: Construction & Expansion

David Paulius, Ahmad Babaeian Jelodar, Yu Sun

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

Comments 7 pages, 3 figures, presented at ICRA 2018

Journal ref ICRA 2018 Submission -- 7 pages

2002.08909 2020-02-21 cs.CL cs.LG 57%

REALM: Retrieval-Augmented Language Model Pre-Training

Kelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat, Ming-Wei Chang

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

1910.14613 2019-11-01 cs.LG cs.CL stat.ML 57%

Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

Arvind Neelakantan, Semih Yavuz, Sharan Narang, Vishaal Prasad, Ben Goodrich, Daniel Duckworth, Chinnadhurai Sankar, Xifeng Yan

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

1906.00300 2019-07-01 cs.CL 57%

Latent Retrieval for Weakly Supervised Open Domain Question Answering

Kenton Lee, Ming-Wei Chang, Kristina Toutanova

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

Comments Accepted to ACL 2019

1906.07108 2019-06-18 cs.CL 57%

Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing

Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, Jian Yin

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

Comments Accepted by ACL 2019

1906.04618 2019-06-12 cs.CL 57%

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

Minghao Hu, Yuxing Peng, Zhen Huang, Dongsheng Li

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

Comments To appear at ACL 2019

1811.11160 2018-11-28 cs.IT cs.CR cs.DB math.IT 57%

The Capacity of Private Information Retrieval from Decentralized Uncoded Caching Databases

Yi-Peng Wei, Batuhan Arasli, Karim Banawan, Sennur Ulukus

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

Comments Submitted for publication, November 2018

cs/0412071 2016-11-17 cs.AI cs.NE 57%

Web Usage Mining Using Artificial Ant Colony Clustering and Genetic Programming

Ajith Abraham, Vitorino Ramos

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

Comments 8 pages, 11 figures, at http://alfa.ist.utl.pt/~cvrm/staff/vramos/ref_48.html

Journal ref CEC 03 - Congress on Evolutionary Computation, IEEE Press, ISBN 0780378040, pp.1384-1391, Canberra, Australia, 8-12 Dec. 2003

1408.0595 2014-08-05 cs.AI 57%

Correlating and Cross-linking Knowledge Threads in Informledge System for Creating New Knowledge

T. R. Gopalakrishnan Nair, Meenakshi Malhotra

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

Comments 6 pages, 6 figures, 3 tables, International Conference on Knowledge Engineering and Ontology Development, 2012

cs/0412075 2009-12-01 cs.AI cs.DC 57%

Self-Organized Stigmergic Document Maps: Environment as a Mechanism for Context Learning

Vitorino Ramos, Juan J. Merelo

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

Comments 10 pages, 5 figures, at http://alfa.ist.utl.pt/~cvrm/staff/vramos/ref_42.html

Journal ref in AEB 2002, 1st Spanish Conference on Evolutionary and Bio-Inspired Algorithms, E. Alba, F. Herrera, J.J. Merelo et al. (Eds.), pp. 284-293, Centro Univ. de Merida, Merida, Spain, 6-8 Feb. 2002

cs/0310011 2009-12-01 cs.HC cs.IR 57%

Re-Finding Found Things: An Exploratory Study of How Users Re-Find Information

Robert G. Capra, Manuel A. Perez-Quinones

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

2601.17333 2026-01-27 cs.IR cs.AI cs.CE cs.DB 56%

FinMetaMind: A Tech Blueprint on NLQ Systems for Financial Knowledge Search

FinMetaMind: 金融知识检索中自然语言查询系统的设计技术蓝图

Lalit Pant, Shivang Nagar

机构 * Independent Author（独立研究者）

专题命中检索器与排序：分类 cs.IR、cs.AI、cs.DB；vector search(comments)

AI总结 FinMetaMind提出了一种针对金融知识检索的NLQ系统设计，通过整合自然语言处理、搜索工程和向量数据模型，解决金融数据检索中的关键挑战。

Comments 8 pages, 8 figures, Information Retrieval, Natural Language Query, Vector Search, Embeddings, Named Entity Recognition, Large Language Models

2608.06722 2026-08-20 cs.HC 版本更新 50%

CustomDance: Customized 3D Dance Generation with Coarse-to-Fine Human-Centered Interactive Control

CustomDance：基于以人为中心的粗到细交互式控制的定制化3D舞蹈生成

Xulong Tang, Kaixing Yang, Xiaohu Guo, Prabhakaran Balakrishnan, Rawan Alghofaili

专题命中检索器与排序：retriever(abstract)

AI总结 CustomDance是基于粗到细交互式控制的定制化3D舞蹈生成系统，通过三阶段流程实现AI辅助编舞，在定量和定性比较中优于基线，为用户提供全面控制。

Comments Accepted to SIGGRAPH Asia 2026

2506.14488 2026-08-17 q-bio.BM cs.LG 版本更新 50%

READ: A Retrieval-Alignment Diffusion Framework for Structure-based Drug Design

READ：一种用于基于结构的药物设计的检索-对齐扩散框架

Dong Xu, Zhangfan Yang, Junchuang Cai, Sisi Yuan, Zexuan Zhu, Jianqiang Li, Junkai Ji

机构 * School of Artificial Intelligence（人工智能学院）； Shenzhen University（深圳大学）； National Engineering Laboratory for Big Data System Computing Technology（大数据系统计算技术国家工程实验室）； School of Computer Science（计算机科学学院）； University of Nottingham Ningbo（诺丁汉大学宁波校区）； Department of Computing（计算学院）

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

AI总结针对现有SBDD模型忽略蛋白-配体复合物相似性及数据有限的问题，提出READ检索-对齐扩散框架，在标准化对接评估中表现优于现有方法，为早期药物计算命中物生成提供实用框架。

Comments 15 pages, 8 figures. Supplementary material is included as an ancillary file. Accepted for publication in IEEE Transactions on Computational Biology and Bioinformatics

Journal ref IEEE Transactions on Computational Biology and Bioinformatics, pp. 1-15, 2026

2608.12419 2026-08-14 cs.LG 新提交 50%

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining

LoKiFormer：面向高效大语言模型预训练的 locality-aware 注意力与解耦知识记忆

Qiuwu Chen, Zimo Liu, Yuchen Li, Ying Sun, Yifan Zhang, Zhijie Qiu, Zeng You, Ryan Dong, Simeng Ma, Yaofo Chen, Mingkui Tan

机构 * AIGCode ； South China University of Technology（华南理工大学）； Pazhou Laboratory（琶洲实验室）

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

AI总结针对LLM预训练效率问题，提出含局部融合注意力与知识记忆模块的LoKiFormer，使预训练收敛速度提升1.33倍，性能优于现有架构。

Comments Accepted by ICML 2026

2608.11592 2026-08-13 cs.RO 新提交 50%

Video2Track: From Real-World Interaction Videos to Steerable Adversarial Closed-Track Testing for Automated Driving Systems

Video2Track：从真实世界交互视频到自动驾驶系统的可操控对抗性封闭赛道测试

Mengjie Tian, Xinrui Zhang, Tianyu Li, Peizhi Zhang, Guirong Zhou, Haojie Feng, Junpeng Huang, Qixiang Zhang, Lu Xiong

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

AI总结本文提出Video2Track框架，通过两个耦合模块将真实驾驶视频交互场景转化为可操控对抗性封闭赛道测试，可复现实景交互场景并生成可控变体，为ADS验证提供可扩展方案。

2608.06060 2026-08-07 cs.CV 新提交 50%

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval

从失败中学习：基于难负例的以检索为中心的思维链用于统一多模态检索

Zelong Sun, Jun Wang, Kaicheng Yang, Tiancheng Gu, Ziyong Feng, Zhiwu Lu

专题命中检索器与排序：retriever(abstract)

AI总结该研究提出UniME-R1框架，通过基于难负例的以检索为中心的思维链（RC-CoT）学习从检索失败中优化，在多模态检索基准上提升了性能。

Comments 26 pages,10 figures,14 Tables

1. 检索器与排序 4563 篇

Teach Me What to Say and I Will Learn What to Pick: Unsupervised Knowledge Selection Through Response Generation with Pretrained Generative Models

Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

Dealing with Typos for BERT-based Passage Retrieval and Ranking

Retrieval Augmented Code Generation and Summarization

Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

Distilling Transformers for Neural Cross-Domain Search

Automatic Claim Review for Climate Science via Explanation Generation

SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

Simple and Efficient ways to Improve REALM

Multi-task Retrieval for Knowledge-Intensive Tasks

MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models

Current Limitations of Language Models: What You Need is Retrieval

Functional Object-Oriented Network: Construction & Expansion

REALM: Retrieval-Augmented Language Model Pre-Training

Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

Latent Retrieval for Weakly Supervised Open Domain Question Answering

Coupling Retrieval and Meta-Learning for Context-Dependent Semantic Parsing

Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension

The Capacity of Private Information Retrieval from Decentralized Uncoded Caching Databases

Web Usage Mining Using Artificial Ant Colony Clustering and Genetic Programming

Correlating and Cross-linking Knowledge Threads in Informledge System for Creating New Knowledge

Self-Organized Stigmergic Document Maps: Environment as a Mechanism for Context Learning

Re-Finding Found Things: An Exploratory Study of How Users Re-Find Information

FinMetaMind: A Tech Blueprint on NLQ Systems for Financial Knowledge Search

CustomDance: Customized 3D Dance Generation with Coarse-to-Fine Human-Centered Interactive Control

READ: A Retrieval-Alignment Diffusion Framework for Structure-based Drug Design

LoKiFormer: Locality-aware Attention with Decoupled Knowledge Memory for Efficient Large Language Model Pretraining

Video2Track: From Real-World Interaction Videos to Steerable Adversarial Closed-Track Testing for Automated Driving Systems

Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval