RAG / 检索增强生成

KunLunBaizeRAG: Reinforcement Learning Driven Inference Performance Leap for Large Language Models

Cheng Li, Jiexiong Liu, Yixuan Chen, Qihang Zhou, KunLun Meta

机构 * KunLun Meta（昆仑元） 纠错

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

TracLLM: A Generic Framework for Attributing Long Context LLMs

Yanting Wang, Wei Zou, Runpeng Geng, Jinyuan Jia

机构 * Pennsylvania State University（宾夕法尼亚州立大学） 纠错

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments To appear in USENIX Security Symposium 2025. The code and data are at: https://github.com/Wang-Yanting/TracLLM

Enhancing Large Language Models with Neurosymbolic Reasoning for Multilingual Tasks

Sina Bagheri Nezhad, Ameeta Agrawal

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments Accepted at 19th Conference on Neurosymbolic Learning and Reasoning (NeSy 2025)

Communication- and Computation-Efficient Distributed Submodular Optimization in Robot Mesh Networks

Zirui Xu, Sandilya Sai Garimella, Vasileios Tzoumas

机构 * Department of Aerospace Engineering, University of Michigan（密歇根大学航空航天工程系） ； Institute for Robotics and Intelligent Machines, Georgia Institute of Technology（佐治亚理工学院机器人与智能机器研究所） ； Department of Robotics, University of Michigan（密歇根大学机器人学系） 纠错

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments Accepted to IEEE Transactions on Robotics

QwenLong-CPRS: Towards $\infty$-LLMs with Dynamic Context Optimization

Weizhou Shen, Chenliang Li, Fanqi Wan, Shengyi Liao, Shaopeng Lai, Bo Zhang, Yingcheng Shi, Yuning Wu, Gang Fu, Zhansheng Li, Bin Yang, Ji Zhang, Fei Huang, Jingren Zhou, Ming Yan

机构 * Tongyi Lab, Alibaba Group（通义实验室，阿里集团） 纠错

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs

Xiabin Zhou, Wenbin Wang, Minyan Zeng, Jiaxian Guo, Xuebo Liu, Li Shen, Min Zhang, Liang Ding

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Flow State: Humans Enabling AI Systems to Program Themselves

Helena Zhang, Jakobi Haskell, Yosef Frost

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments 25 pages, 4 figures, 5 tables. Describes a minimalist framework for human-AI co-design of compound AI systems

CONSTRUCTA: Automating Commercial Construction Schedules in Fabrication Facilities with Large Language Models

Yifan Zhang, Xue Yang

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

LLMmap: Fingerprinting For Large Language Models

Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments Appearing in the proceedings of the 34th USENIX Security Symposium

Perception Compressor: A Training-Free Prompt Compression Framework in Long Context Scenarios

Jiwei Tang, Jin Xu, Tingwei Lu, Zhicheng Zhang, Yiming Zhao, Lin Hai, Hai-Tao Zheng

专题命中 长文档RAG ：retriever(abstract)；分类 cs.CL

Comments Accepted at NAACL 2025 Findings

Practical Design and Benchmarking of Generative AI Applications for Surgical Billing and Coding

John C. Rollman, Bruce Rogers, Hamed Zaribafzadeh, Daniel Buckland, Ursula Rogers, Jennifer Gagnon, Ozanan Meireles, Lindsay Jennings, Jim Bennett, Jennifer Nicholson, Nandan Lad, Linda Cendales, Andreas Seas, Alessandro Martinino, E. Shelley Hwang, Allan D. Kirk

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments 21 pages, 3 figures, 2 tables

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression

Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Xinting Huang, Dong Yu, Zhicheng Dou

专题命中 长文档RAG ：retrieval-augmented generation(abstract)；分类 cs.CL

Fine-tuning Large Language Models for Domain-specific Machine Translation

Jiawei Zheng, Hanghai Hong, Feiyan Liu, Xiaoli Wang, Jingsong Su, Yonggui Liang, Shikai Wu

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments 13 pages, 5 figures, 9 tables

On the Way to LLM Personalization: Learning to Remember User Conversations

Lucie Charlotte Magister, Katherine Metcalf, Yizhe Zhang, Maartje ter Hoeve

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments 16 pages, 6 tables, 3 figures

LongEmbed: Extending Embedding Models for Long Context Retrieval

Dawei Zhu, Liang Wang, Nan Yang, Yifan Song, Wenhao Wu, Furu Wei, Sujian Li

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments EMNLP 2024 Camera Ready

RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation

Ian Poey, Jiajun Liu, Qishuai Zhong, Adrien Chenailler

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

PDL: A Declarative Prompt Programming Language

Mandana Vaziri, Louis Mandel, Claudio Spiess, Martin Hirzel

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices

Ruiyang Qin, Dancheng Liu, Chenhui Xu, Zheyu Yan, Zhaoxuan Tan, Zhenge Jia, Amir Nassereldine, Jiajie Li, Meng Jiang, Ahmed Abbasi, Jinjun Xiong, Yiyu Shi

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments Benckmarking paper

SwiftDossier: Tailored Automatic Dossier for Drug Discovery with LLMs and Agents

Gabriele Fossi, Youssef Boulaimen, Leila Outemzabet, Nathalie Jeanray, Stephane Gerart, Sebastien Vachenc, Joanna Giemza, Salvatore Raieli

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments 10 pages, 7 figures, 2 tables

MaxMind: A Memory Loop Network to Enhance Software Productivity based on Large Language Models

Yuchen Dong, XiaoXiang Fang, Yuchen Hu, Renshuang Jiang, Zhe Jiang

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Recording First-person Experiences to Build a New Type of Foundation Model

Dionis Barcari, David Gamez, Aliya Grig

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments 5 pages, 5 figures, 3 tables. arXiv admin note: substantial text overlap with arXiv:2408.00030

A New Type of Foundation Model Based on Recordings of People's Emotions and Physiology

David Gamez, Dionis Barcari, Aliya Grig

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Comments 12 pages, 2 figures, 3 tables

S$^3$HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering

Fangyu Lei, Xiang Li, Yifan Wei, Shizhu He, Yiming Huang, Jun Zhao, Kang Liu

专题命中 长文档RAG ：retriever(abstract)；分类 cs.CL

Comments ACL 2023

Exploring Fact Memorization and Style Imitation in LLMs Using QLoRA: An Experimental Study and Quality Assessment Methods

Eugene Vyborov, Oleksiy Osypenko, Serge Sotnyk

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments 16 pages, 5 tables

APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning

Jiashuo Sun, Hang Zhang, Chen Lin, Xiangdong Su, Yeyun Gong, Jian Guo

专题命中 长文档RAG ：retriever(abstract)；分类 cs.CL

Comments Accepted by COLING 2024

Few-Shot Fairness: Unveiling LLM's Potential for Fairness-Aware Classification

Garima Chhikara, Anurag Sharma, Kripabandhu Ghosh, Abhijnan Chakraborty

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Comments Under review

GenDec: A robust generative Question-decomposition method for Multi-hop reasoning

Jian Wu, Linyi Yang, Yuliang Ji, Wenhao Huang, Börje F. Karlsson, Manabu Okumura

专题命中 长文档RAG ：RAG(abstract)；分类 cs.CL

Robust Action Governor for Uncertain Piecewise Affine Systems with Non-convex Constraints and Safe Reinforcement Learning

Yutong Li, Nan Li, H. Eric Tseng, Anouck Girard, Dimitar Filev, Ilya Kolmanovsky

专题命中 长文档RAG ：RAG(abstract)；分类 cs.AI

Efficient Nehari manifold optimization algorithms for computing ground state solutions of nonlinear elliptic systems

高效Nehari流形优化算法用于计算非线性椭圆系统的基态解

Zhaoxing Chen, Wei Liu, Ziqing Xie, Wenfan Yi

专题命中 长文档RAG ：RAG(abstract)

AI总结 本文提出了一种高效的Nehari流形优化算法，用于计算半线性椭圆系统的基态解，通过结合NMOM与Nesterov加速方法，改进了稳定性与计算效率。

Comments 26 pages, 17 figures

IOAgent: Democratizing Trustworthy HPC I/O Performance Diagnosis Capability via LLMs

IOAgent: 通过LLMs普及可信的HPC I/O性能诊断能力

Chris Egersdoerfer, Arnav Sareen, Jean Luca Bez, Suren Byna, Dongkuan Xu, Dong Dai

专题命中 长文档RAG ：RAG(abstract)

AI总结 IOAgent通过LLMs实现HPC I/O性能诊断的自动化，提供准确诊断和交互接口，提升领域科学家的生产力。

Comments Published in the Proceedings of the 2025 IEEE International Parallel and Distributed Processing Symposium (IPDPS 2025)