RAG / 检索增强生成 - arXivDaily 专题

2203.09424 2022-10-05 cs.CL 57%

elBERto: Self-supervised Commonsense Learning for Question Answering

Xunlin Zhan, Yuan Li, Xiao Dong, Xiaodan Liang, Zhiting Hu, Lawrence Carin

专题命中知识库问答：knowledge retrieval(abstract)；分类 cs.CL

2202.13296 2022-07-28 cs.CL 57%

Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering

Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, Hong Chen

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments The experimental results are updated by fixing the data leakage issue in the code

2207.01940 2022-07-19 cs.CL 57%

MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering

Zhucheng Tu, Sarguna Janani Padmanabhan

专题命中知识库问答：dense retrieval(abstract)；分类 cs.CL

Comments System description for the Multilingual Information Access 2022 Shared Task

2109.13087 2022-06-22 cs.CL 57%

Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations

Wei Chen, Yeyun Gong, Can Xu, Huang Hu, Bolun Yao, Zhongyu Wei, Zhihao Fan, Xiaowu Hu, Bartuer Zhou, Biao Cheng, Daxin Jiang, Nan Duan

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Journal ref ACL 2022

2110.04330 2022-06-07 cs.CL cs.LG 57%

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments Accepted by ACL 2022

2112.08688 2022-05-17 cs.CL 57%

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

Akari Asai, Matt Gardner, Hannaneh Hajishirzi

专题命中知识库问答：retrieval-augmented generation(abstract)；分类 cs.CL

Comments Published as a conference paper at NAACL 2022 (long). Code available at https://github.com/AkariAsai/evidentiality_qa

2112.08614 2022-05-06 cs.CL 57%

KAT: A Knowledge Augmented Transformer for Vision-and-Language

Liangke Gui, Borui Wang, Qiuyuan Huang, Alex Hauptmann, Yonatan Bisk, Jianfeng Gao

专题命中知识库问答：knowledge retrieval(abstract)；分类 cs.CL

Comments Accepted by NAACL 2022

2012.14610 2022-05-05 cs.CL 57%

UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

Barlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments NAACL-HLT 2022 Findings

2203.08928 2022-03-23 cs.CL 57%

C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References

Xiang Yue, Xiaoman Pan, Wenlin Yao, Dian Yu, Dong Yu, Jianshu Chen

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments ACL 2022 Main Conference

2110.15439 2021-11-01 cs.IR 57%

Dense Hierarchical Retrieval for Open-Domain Question Answering

Ye Liu, Kazuma Hashimoto, Yingbo Zhou, Semih Yavuz, Caiming Xiong, Philip S. Yu

专题命中知识库问答：retriever(abstract)；分类 cs.IR

Comments EMNLP 2021 Findings

2110.04889 2021-10-12 cs.CL 57%

Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, Hal Daumé

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments EMNLP 2021

2109.10346 2021-09-22 cs.CL cs.LG 57%

Relation-Guided Pre-Training for Open-Domain Question Answering

Ziniu Hu, Yizhou Sun, Kai-Wei Chang

专题命中知识库问答：retriever(abstract)；分类 cs.CL

2109.02905 2021-09-08 cs.CL 57%

Exploiting Reasoning Chains for Multi-hop Science Question Answering

Weiwen Xu, Yang Deng, Huihui Zhang, Deng Cai, Wai Lam

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments 14 pages, Findings of EMNLP 2021

2012.12624 2021-06-03 cs.CL 57%

Learning Dense Representations of Phrases at Scale

Jinhyuk Lee, Mujeen Sung, Jaewoo Kang, Danqi Chen

专题命中知识库问答：retriever(abstract)；分类 cs.CL

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

2105.11776 2021-05-26 cs.CL 57%

Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering

Weiwen Xu, Huihui Zhang, Deng Cai, Wai Lam

专题命中知识库问答：knowledge retrieval(abstract)；分类 cs.CL

Comments Accepted by Findings of ACL 2021

2103.06332 2021-05-20 cs.CL cs.LG 57%

Hurdles to Progress in Long-form Question Answering

Kalpesh Krishna, Aurko Roy, Mohit Iyyer

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments NAACL 2021 camera ready (18 pages)

2101.00774 2021-05-11 cs.AI 57%

Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

Fengbin Zhu, Wenqiang Lei, Chao Wang, Jianming Zheng, Soujanya Poria, Tat-Seng Chua

专题命中知识库问答：retriever(abstract)；分类 cs.AI

2005.00038 2021-02-22 cs.CL 57%

Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering

Wenhan Xiong, Hong Wang, William Yang Wang

专题命中知识库问答：dense retrieval(abstract)；分类 cs.CL

Comments EACL 2021

2012.15156 2021-01-01 cs.CL 57%

A Memory Efficient Baseline for Open Domain Question Answering

Gautier Izacard, Fabio Petroni, Lucas Hosseini, Nicola De Cao, Sebastian Riedel, Edouard Grave

专题命中知识库问答：retriever(abstract)；分类 cs.CL

2006.08337 2020-10-26 cs.CL 57%

Open-Domain Question Answering with Pre-Constructed Question Spaces

Jinfeng Xiao, Lidan Wang, Franck Dernoncourt, Trung Bui, Tong Sun, Jiawei Han

专题命中知识库问答：retriever(abstract)；分类 cs.CL

2004.04906 2020-10-02 cs.CL 57%

Dense Passage Retrieval for Open-Domain Question Answering

Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments EMNLP 2020

2009.13013 2020-09-29 cs.CL cs.LG 57%

SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval

Tiancheng Zhao, Xiaopeng Lu, Kyusong Lee

专题命中知识库问答：vector search(abstract)；分类 cs.CL

Comments 11 pages

2002.12591 2020-03-02 cs.CL 57%

DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding

Yuyu Zhang, Ping Nie, Xiubo Geng, Arun Ramamurthy, Le Song, Daxin Jiang

专题命中知识库问答：retriever(abstract)；分类 cs.CL

1911.10470 2020-02-17 cs.CL 57%

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

Akari Asai, Kazuma Hashimoto, Hannaneh Hajishirzi, Richard Socher, Caiming Xiong

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments Published as a conference paper at ICLR 2020. Code is available at https://github.com/AkariAsai/learning_to_retrieve_reasoning_paths

1906.05394 2019-06-14 cs.CL cs.LG 57%

Neural Arabic Question Answering

Hussein Mozannar, Karl El Hajal, Elie Maamary, Hazem Hajj

专题命中知识库问答：retriever(abstract)；分类 cs.CL

Comments WANLP 2019

1804.07942 2018-09-21 cs.CL 57%

Generative Stock Question Answering

Zhaopeng Tu, Yong Jiang, Xiaojiang Liu, Lei Shu, Shuming Shi

专题命中知识库问答：hybrid retrieval(abstract)；分类 cs.CL

Comments data: http://ai.tencent.com/ailab/nlp/data/stockQA.tar.gz

1809.02789 2018-09-11 cs.CL 57%

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Todor Mihaylov, Peter Clark, Tushar Khot, Ashish Sabharwal

专题命中知识库问答：knowledge retrieval(abstract)；分类 cs.CL

Comments Published as conference long paper at EMNLP 2018

2404.14464 2024-04-24 cs.CL cs.AI cs.IR 56%

Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering

Li Jiapeng, Liu Runze, Li Yabo, Zhou Tong, Li Mingling, Chen Xiang

专题命中知识库问答：分类 cs.IR、cs.CL、cs.AI；retrieval-augmented generation(comments)

Comments Keywords: Muti-hop Question Answering; Retrieval-Augmented Generation; Tree of Thought; Reasoning TLDR: We proposed a tree-based dynamic, iterative retrieval framework for multi-hop question answering

2511.11132 2026-07-15 cs.CV 版本更新 50%

From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering

从回顾到前瞻：面向知识驱动视觉问答的自我鼓励回顾蒸馏

Yu Zhao, Ying Zhang, Xuhui Sui, Baohang Zhou, Xinying Qian, Li Shen, Dacheng Tao

机构 * College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）

专题命中知识库问答：retrieval augmented generation(abstract)

AI总结本文提出HinD框架，通过知识鼓励偏好优化提升多模态大语言模型的知识推理能力，实验表明其在OK-VQA和A-OKVQA上表现优异。

2601.14556 2026-01-22 cs.LG cs.CR 50%

Constructing Multi-label Hierarchical Classification Models for MITRE ATT&CK Text Tagging

构建MITRE ATT&CK文本标记的多标签分层分类模型

Andrew Crossman, Jonah Dodd, Viralam Ramamurthy Chaithanya Kumar, Riyaz Mohammed, Andrew R. Plummer, Chandra Sekharudu, Deepak Warrier, Mohammad Yekrangian

机构 * JPMorganChase（摩根大通）

专题命中知识库问答：RAG(abstract)

AI总结本文提出了一种基于经典机器学习的多标签分层分类模型，用于MITRE ATT&CK文本标记，实现了94%的战术层面准确率和82%的技术层面准确率，且无需依赖LLM等复杂方法。

1. 知识库问答 545 篇

elBERto: Self-supervised Commonsense Learning for Question Answering

Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering

MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering

Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations

KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks

KAT: A Knowledge Augmented Transformer for Vision-and-Language

UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering

C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of References

Dense Hierarchical Retrieval for Open-Domain Question Answering

Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Relation-Guided Pre-Training for Open-Domain Question Answering

Exploiting Reasoning Chains for Multi-hop Science Question Answering

Learning Dense Representations of Phrases at Scale

Dynamic Semantic Graph Construction and Reasoning for Explainable Multi-hop Science Question Answering

Hurdles to Progress in Long-form Question Answering

Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering

A Memory Efficient Baseline for Open Domain Question Answering

Open-Domain Question Answering with Pre-Constructed Question Spaces

Dense Passage Retrieval for Open-Domain Question Answering

SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching Retrieval

DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding

Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answering

Neural Arabic Question Answering

Generative Stock Question Answering

Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answering

From Hindsight to Foresight: Self-Encouraged Hindsight Distillation for Knowledge-based Visual Question Answering

Constructing Multi-label Hierarchical Classification Models for MITRE ATT&CK Text Tagging