RAG / 检索增强生成

Enhancing Cache-Augmented Generation (CAG) with Adaptive Contextual Compression for Scalable Knowledge Integration

Rishabh Agrawal, Himanshu Kumar

机构 * Data Science（数据科学） ； Marketing Data Scientist（市场数据科学家） 纠错

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

Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models

Shuyang Hou, Anqi Zhao, Jianyuan Liang, Zhangxiao Shen, Huayi Wu

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI、cs.DB

An Analysis of Decoding Methods for LLM-based Agents for Faithful Multi-Hop Question Answering

Alexander Murphy, Mohd Sanad Zaki Rizvi, Aden Haussmann, Ping Nie, Guifu Liu, Aryo Pradipta Gema, Pasquale Minervini

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

QMOS: Enhancing LLMs for Telecommunication with Question Masked loss and Option Shuffling

Blessed Guda, Gabrial Zencha Ashungafac, Lawrence Francis, Carlee Joe-Wong

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Journal ref IEEE Globecom Workshop 2024

Passage Segmentation of Documents for Extractive Question Answering

Zuhong Liu, Charles-Elie Simon, Fabien Caspani

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

GEE-OPs: An Operator Knowledge Base for Geospatial Code Generation on the Google Earth Engine Platform Powered by Large Language Models

Shuyang Hou, Jianyuan Liang, Anqi Zhao, Huayi Wu

专题命中 知识库问答 ：retrieval-augmented generation(abstract)；RAG(abstract)；分类 cs.AI、cs.DB

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering

Yuhao Wang, Ruiyang Ren, Junyi Li, Wayne Xin Zhao, Jing Liu, Ji-Rong Wen

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

Comments Accepted to EMNLP 2024 Main Conference. Published on ACL Anthology: https://aclanthology.org/2024.emnlp-main.321.pdf

JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking

Tong Niu, Shafiq Joty, Ye Liu, Caiming Xiong, Yingbo Zhou, Semih Yavuz

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

LLM Robustness Against Misinformation in Biomedical Question Answering

Alexander Bondarenko, Adrian Viehweger

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

Enhancing Retrieval in QA Systems with Derived Feature Association

Keyush Shah, Abhishek Goyal, Isaac Wasserman

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.CL

Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA

Minzheng Wang, Longze Chen, Cheng Fu, Shengyi Liao, Xinghua Zhang, Bingli Wu, Haiyang Yu, Nan Xu, Lei Zhang, Run Luo, Yunshui Li, Min Yang, Fei Huang, Yongbin Li

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments EMNLP 2024 Main. We release our code and data publicly at https://github.com/MozerWang/Loong

QPaug: Question and Passage Augmentation for Open-Domain Question Answering of LLMs

Minsang Kim, Cheoneum Park, Seungjun Baek

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

Comments The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), Findings

Learning When to Retrieve, What to Rewrite, and How to Respond in Conversational QA

Nirmal Roy, Leonardo F. R. Ribeiro, Rexhina Blloshmi, Kevin Small

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

Comments Accepted in EMNLP (findings) 2024

Towards Human-Level Understanding of Complex Process Engineering Schematics: A Pedagogical, Introspective Multi-Agent Framework for Open-Domain Question Answering

Sagar Srinivas Sakhinana, Geethan Sannidhi, Venkataramana Runkana

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments Our paper is accepted for publication at ML4CCE workshop at ECML PKDD 2024

GenSco: Can Question Decomposition based Passage Alignment improve Question Answering?

Barah Fazili, Koustava Goswami, Natwar Modani, Inderjeet Nair

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.IR、cs.CL

Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway

Hamed Babaei Giglou, Tilahun Abedissa Taffa, Rana Abdullah, Aida Usmanova, Ricardo Usbeck, Jennifer D'Souza, Sören Auer

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments 13 pages main content, 16 pages overall, 3 Figures, accepted for publication at NSLP 2024 workshop at ESWC 2024

CorpusLM: Towards a Unified Language Model on Corpus for Knowledge-Intensive Tasks

Xiaoxi Li, Zhicheng Dou, Yujia Zhou, Fangchao Liu

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

TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction

Shuo Li, Sangdon Park, Insup Lee, Osbert Bastani

专题命中 知识库问答 ：retrieval augmented generation(abstract)；RAG(abstract)；分类 cs.CL、cs.AI

Comments 23 pages, 17 figures, 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics

MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering

Che Guan, Mengyu Huang, Peng Zhang

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

Comments 8 pages

Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task

Linghan Zheng, Hui Liu, Xiaojun Lin, Jiayuan Dong, Yue Sheng, Gang Shi, Zhiwei Liu, Hongwei Chen

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

Few-shot Reranking for Multi-hop QA via Language Model Prompting

Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang

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

Comments ACL 2023 - Camera Ready

Huatuo-26M, a Large-scale Chinese Medical QA Dataset

Jianquan Li, Xidong Wang, Xiangbo Wu, Zhiyi Zhang, Xiaolong Xu, Jie Fu, Prayag Tiwari, Xiang Wan, Benyou Wang

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

End-to-End Training of Neural Retrievers for Open-Domain Question Answering

Devendra Singh Sachan, Mostofa Patwary, Mohammad Shoeybi, Neel Kant, Wei Ping, William L Hamilton, Bryan Catanzaro

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

Comments ACL 2021

AaLLM: An End-to-End Analog Circuit Design Framework from Topology Generation to Sizing Using Large Language Models

AaLLM：基于大语言模型的从拓扑生成到尺寸确定的端到端模拟电路设计框架

Mohammed Ayman Habib, Rylan Hart, Morteza Fayazi

专题命中 知识库问答 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 本文提出AaLLM，一种端到端多智能体LLM工作流，自动完成模拟电路拓扑生成与尺寸确定，可减少SPICE调用次数和运行时间，创新拓扑性能与传统拓扑相当。

One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA

每个多模态证据一个令牌：面向资源受限问答的潜在记忆

Zhi Zheng, Ziqiao Meng, Hao Luan, Wei Liu, Wee Sun Lee

机构 * School of Computing, National University of Singapore（新加坡国立大学计算机学院） 纠错

专题命中 知识库问答 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 提出潜在记忆范式，将每个证据压缩为单个高维潜在令牌，通过统一训练实现高效检索与生成，在资源受限场景下以3-10倍令牌节省达到竞争性问答性能。

Asking For An Old Friend: Diagnosing and Mitigating Temporal Failure Modes in LLM-based Statutory Question Answering

询问老朋友：诊断和缓解基于LLM的法定问答中的时间故障模式

Max Prior, Andreas Schultz, Matthias Grabmair

机构 * Technical University of Munich（慕尼黑技术大学） 纠错

专题命中 知识库问答 ：RAG(abstract,abstract_cn)；分类 cs.CL

AI总结 本研究通过构建包含312个专家验证的德国法定问答对基准，诊断并缓解了大型语言模型在法定问答中的两种时间故障模式（截止后过时和近因偏差），发现检索增强生成通过事实日期提取和版本过滤显著提升性能，而网络搜索存在不稳定性与近因偏差。

Enabling Collaborative Parametric Knowledge Calibration for Retrieval-Augmented Vision Question Answering

使检索增强的视觉问答实现协作参数知识校准

Jiaqi Deng, Kaize Shi, Zonghan Wu, Huan Huo, Dingxian Wang, Guandong Xu

机构 * University of Technology Sydney（悉尼大学） ； East China Normal University（华东师范大学） ； The Education University of Hong Kong（香港教育大学） 纠错

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

AI总结 本文提出了一种统一的检索增强视觉问答框架，通过协作参数知识校准来充分利用KB-VQA中的跨任务协同效应，从而提升问答准确性。

Comments 10 pages, 5 figures, Under Review

Journal ref Knowledge-Based Systems, 8 July 2026, Volume 346

Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise

通过卡尔曼滤波、克里格法和过程噪声的精确跟踪变压器

Bo Long, Deepak Agarwal, Jelena Markovic-Voronov, Yi Wang, Liuqing Li

机构 * LinkedIn Core AI（LinkedIn核心AI） 纠错

专题命中 知识库问答 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 本文提出了一种基于贝叶斯滤波的变压器（BFT），通过引入精度权重的克里格法、自适应卡尔曼更新和动态模型，解决了传统变压器在处理不确定性方面的不足，提升了序列推荐和大语言模型在噪声环境下的鲁棒性。

Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations

grounded continuation: 一种线性时间的运行时验证器用于大语言模型对话

Qisong He, Yi Dong, Xiaowei Huang

机构 * School of Computer Science and Informatics, University of Liverpool, UK（利兹大学计算机科学与信息学学院） 纠错

专题命中 知识库问答 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 本文提出一种线性时间的运行时验证器，用于检测大语言模型对话中基于已废弃前提的延续。通过显式依赖图验证，该方法在LongMemEval-KU和LoCoMo基准上表现出色，准确率显著高于基线模型。

SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory

SAGE：一种自演化代理图记忆引擎，用于结构感知的联想记忆

Juntong Wang, Haoyue Zhao, guanghui Pan, Xiyuan Wang, Yanbo Wang, Qiyan Deng, Muhan Zhang

机构 * Institute for Artificial Intelligence, Peking University（北京大学人工智能研究院） ； School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学校） ； School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学校） 纠错

专题命中 知识库问答 ：RAG(abstract,abstract_cn)；分类 cs.AI

AI总结 SAGE通过自演化机制和图记忆引擎提升长期记忆能力，在多跳问答、开放领域检索等任务中表现出色，显著提高了证据恢复和检索效率。