RAG / 检索增强生成 - arXivDaily 专题

2312.02538 2024-01-17 cs.IR 79%

A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval

Xiaojie Sun, Keping Bi, Jiafeng Guo, Sihui Yang, Qishen Zhang, Zhongyi Liu, Guannan Zhang, Xueqi Cheng

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

Comments Accepted by WSDM2024, update

2304.08138 2023-11-28 cs.IR 79%

Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval

Shengyao Zhuang, Linjun Shou, Jian Pei, Ming Gong, Houxing Ren, Guido Zuccon, Daxin Jiang

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

Comments 10 pages, accepted at SIGIR-AP

2311.03798 2023-11-08 cs.CL 79%

Noisy Pair Corrector for Dense Retrieval

Hang Zhang, Yeyun Gong, Xingwei He, Dayiheng Liu, Daya Guo, Jiancheng Lv, Jian Guo

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

Comments Findings of EMNLP 2023

2212.09146 2023-11-06 cs.CL 79%

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

Parishad BehnamGhader, Santiago Miret, Siva Reddy

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

Comments Accepted in EMNLP2023 Findings

2212.09114 2023-10-31 cs.CL 79%

CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion

Xingwei He, Yeyun Gong, A-Long Jin, Hang Zhang, Anlei Dong, Jian Jiao, Siu Ming Yiu, Nan Duan

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

Comments Accetpted to EMNLP 2023

2305.15720 2023-10-24 cs.IR 79%

Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors

George Zerveas, Navid Rekabsaz, Carsten Eickhoff

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

Comments EMNLP 2023

2305.06983 2023-10-24 cs.CL cs.LG 79%

Active Retrieval Augmented Generation

Zhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, Graham Neubig

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

Comments EMNLP 2023

2310.13262 2023-10-23 cs.CL 79%

A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation

Xue Zhang, Songming Zhang, Yunlong Liang, Yufeng Chen, Jian Liu, Wenjuan Han, Jinan Xu

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

Comments Accepted to EMNLP 2023

2308.04711 2023-10-16 cs.CL 79%

Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval

Tim Hartill, Diana Benavides-Prado, Michael Witbrock, Patricia J. Riddle

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

2308.11474 2023-08-23 cs.IR 79%

Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval

Xiaojie Sun, Keping Bi, Jiafeng Guo, Xinyu Ma, Fan Yixing, Hongyu Shan, Qishen Zhang, Zhongyi Liu

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

Comments accepted by cikm2023

2308.10191 2023-08-22 cs.IR 79%

Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval

Xueru Wen, Xiaoyang Chen, Xuanang Chen, Ben He, Le Sun

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

Comments Accepted at SIGIR2023

2308.03365 2023-08-15 cs.CL 79%

Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever

Shijue Huang, Bingbing Wang, Libo Qin, Qin Zhao, Ruifeng Xu

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

Comments Accepted to NLPCC2023

2209.00218 2023-08-01 cs.CL 79%

Isotropic Representation Can Improve Dense Retrieval

Euna Jung, Jungwon Park, Jaekeol Choi, Sungyoon Kim, Wonjong Rhee

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

Comments 9 pages, 4 figures

2305.17331 2023-05-30 cs.CL cs.LG 79%

Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In

Zichun Yu, Chenyan Xiong, Shi Yu, Zhiyuan Liu

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

Comments Accepted to ACL 2023

2305.04320 2023-05-17 cs.CL 79%

Unified Demonstration Retriever for In-Context Learning

Xiaonan Li, Kai Lv, Hang Yan, Tianyang Lin, Wei Zhu, Yuan Ni, Guotong Xie, Xiaoling Wang, Xipeng Qiu

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

Comments ACL 2023 camera ready version

2304.14856 2023-05-01 cs.IR 79%

A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning

Jiangui Chen, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Yiqun Liu, Yixing Fan, Xueqi Cheng

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

Comments Accepted by SIGIR 2023

2304.05845 2023-04-13 cs.CL 79%

Rethinking Dense Retrieval's Few-Shot Ability

Si Sun, Yida Lu, Shi Yu, Xiangyang Li, Zhonghua Li, Zhao Cao, Zhiyuan Liu, Deiming Ye, Jie Bao

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

Comments Work in progress

2206.14649 2023-03-30 cs.IR cs.LG 79%

Cooperative Retriever and Ranker in Deep Recommenders

Xu Huang, Defu Lian, Jin Chen, Zheng Liu, Xing Xie, Enhong Chen

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

Comments 12pages, 4 figures, WWW'23

2112.06400 2023-03-22 cs.IR 79%

Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study

Hang Li, Shengyao Zhuang, Ahmed Mourad, Xueguang Ma, Jimmy Lin, Guido Zuccon

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

Comments Accepted at ECIR 2022

2208.13661 2023-03-06 cs.CL 79%

LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval

Kai Zhang, Chongyang Tao, Tao Shen, Can Xu, Xiubo Geng, Binxing Jiao, Daxin Jiang

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

Comments 14 pages, 6 tables, 4 figures. WWW 2023

2301.12400 2023-02-09 cs.AI 79%

HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots

Bolin Zhang, Yunzhe Xu, Zhiying Tu, Dianhui Chu

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

2212.06552 2022-12-14 cs.IR 79%

Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling

Minghan Li, Eric Gaussier

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

Comments 16 pages

2211.08614 2022-11-17 cs.IR cs.HC 79%

H2-Golden-Retriever: Methodology and Tool for an Evidence-Based Hydrogen Research Grantsmanship

Paul Seurin, Olusola Olabanjo, Joseph Wiggins, Lorien Pratt, Loveneesh Rana, Rozhin Yasaei, Gregory Renard

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

Comments 25 pages

2211.03790 2022-11-09 cs.RO cs.AI 79%

Knowledge Retrieval using Foon

Vara Bhavya Sri Malli

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

Comments arXiv admin note: text overlap with arXiv:1902.01537 by other authors. text overlap with arXiv:2211.02992

2210.17167 2022-11-01 cs.CL 79%

Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives

Si Sun, Chenyan Xiong, Yue Yu, Arnold Overwijk, Zhiyuan Liu, Jie Bao

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

Comments Accepted to EMNLP 2022 main conference

2110.03611 2022-11-01 cs.CL 79%

Adversarial Retriever-Ranker for dense text retrieval

Hang Zhang, Yeyun Gong, Yelong Shen, Jiancheng Lv, Nan Duan, Weizhu Chen

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

Comments ICLR 2022

2210.11708 2022-10-24 cs.CL 79%

Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning

Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, SM Yiu, Nan Duan

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

2203.11163 2022-10-24 cs.IR 79%

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval

Wei Zhong, Jheng-Hong Yang, Yuqing Xie, Jimmy Lin

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

2202.07280 2022-10-20 cs.CL 79%

Saving Dense Retriever from Shortcut Dependency in Conversational Search

Sungdong Kim, Gangwoo Kim

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

Comments Accepted to EMNLP 2022 main conference

2208.09846 2022-08-23 cs.IR 79%

A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval

Xinyu Ma, Ruqing Zhang, Jiafeng Guo, Yixing Fan, Xueqi Cheng

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

Comments Accepted by CIKM2022

1. 检索器与排序 4551 篇

A Multi-Granularity-Aware Aspect Learning Model for Multi-Aspect Dense Retrieval

Typos-aware Bottlenecked Pre-Training for Robust Dense Retrieval

Noisy Pair Corrector for Dense Retrieval

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion

Enhancing the Ranking Context of Dense Retrieval Methods through Reciprocal Nearest Neighbors

Active Retrieval Augmented Generation

A Quality-based Syntactic Template Retriever for Syntactically-controlled Paraphrase Generation

Answering Unseen Questions With Smaller Language Models Using Rationale Generation and Dense Retrieval

Pre-training with Aspect-Content Text Mutual Prediction for Multi-Aspect Dense Retrieval

Offline Pseudo Relevance Feedback for Efficient and Effective Single-pass Dense Retrieval

Improving Few-shot and Zero-shot Entity Linking with Coarse-to-Fine Lexicon-based Retriever

Isotropic Representation Can Improve Dense Retrieval

Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-In

Unified Demonstration Retriever for In-Context Learning

A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning

Rethinking Dense Retrieval's Few-Shot Ability

Cooperative Retriever and Ranker in Deep Recommenders

Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback: A Reproducibility Study

LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval

HeroNet: A Hybrid Retrieval-Generation Network for Conversational Bots

Domain Adaptation for Dense Retrieval through Self-Supervision by Pseudo-Relevance Labeling

H2-Golden-Retriever: Methodology and Tool for an Evidence-Based Hydrogen Research Grantsmanship

Knowledge Retrieval using Foon

Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives

Adversarial Retriever-Ranker for dense text retrieval

Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning

Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval

Saving Dense Retriever from Shortcut Dependency in Conversational Search

A Contrastive Pre-training Approach to Learn Discriminative Autoencoder for Dense Retrieval