语言大模型 / LLM - arXivDaily 专题

2409.00872 2025-04-22 cs.CL 70%

Self-evolving Agents with reflective and memory-augmented abilities

Xuechen Liang, Yangfan He, Yinghui Xia, Xinyuan Song, Jianhui Wang, Meiling Tao, Li Sun, Xinhang Yuan, Jiayi Su, Keqin Li, Jiaqi Chen, Jinsong Yang, Siyuan Chen, Tianyu Shi

机构 * East China Jiao Tong University（东中国交通大学）； University of Minnesota - Twin Cities（明尼苏达大学-双城分校）； Emory University（埃默里大学）； University of Electronic Science and Technology of China（电子科技大学）； Guangdong University of Technology（广东工业大学）； Amazon（亚马逊）； Washington University（华盛顿大学）； Xiamen University（厦门大学）； University of Bristol（布里斯托尔大学）； University of Toronto（多伦多大学）

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2503.19271 2025-04-10 cs.CL cs.CV 70%

MARS: Memory-Enhanced Agents with Reflective Self-improvement

Xuechen Liang, Meiling Tao, Yinghui Xia, Jianhui Wang, Kun Li, Yijin Wang, Jingsong Yang, Tianyu Shi, Yuantao Wang, Miao Zhang, Xueqian Wang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments We are withdrawing this version because it duplicates our previous submission (arXiv:2409.00872)

2504.00221 2025-04-09 cs.HC cs.AI cs.CV 70%

GazeLLM: Multimodal LLMs incorporating Human Visual Attention

Jun Rekimoto

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Journal ref Augmented Humans 2025

2403.13164 2025-04-02 cs.LG 70%

VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning

Yongshuo Zong, Ondrej Bohdal, Timothy Hospedales

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments ICLR 2025

2503.22985 2025-04-01 cs.CL 70%

FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering

Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Bin Liang, Binyang Li, Kam-Fai Wong

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2503.20950 2025-03-28 cs.AI 70%

DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Care

Yutong Song, Chenhan Lyu, Pengfei Zhang, Sabine Brunswicker, Nikil Dutt, Amir Rahmani

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted by AAAI 2025 Workshop on Knowledge Graphs for Personalized Public Health

2412.18860 2025-03-20 cs.CL cs.IR 70%

Bootstrap Your Own Context Length

Liang Wang, Nan Yang, Xingxing Zhang, Xiaolong Huang, Furu Wei

专题命中长上下文与记忆：language model(abstract)；instruction tuning(abstract)；分类 cs.CL

Comments 19 pages

2409.02465 2025-03-17 cs.CL 70%

DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels

Zhe Xu, Jiasheng Ye, Xiaoran Liu, Xiangyang Liu, Tianxiang Sun, Zhigeng Liu, Qipeng Guo, Linlin Li, Qun Liu, Xuanjing Huang, Xipeng Qiu

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2503.05850 2025-03-11 cs.CR cs.CV cs.LG 70%

Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis

Sefik Serengil, Alper Ozpinar

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.LG

2503.00870 2025-03-10 cs.AI 70%

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

Wonje Choi, Jinwoo Park, Sanghyun Ahn, Daehee Lee, Honguk Woo

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted at ICLR 2025. Project site with code: https://pjw971022.github.io/nesyc/

2503.04355 2025-03-07 cs.CL 70%

Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling

Zhenghua Wang, Yiran Ding, Changze Lv, Zhibo Xu, Tianlong Li, Tianyuan Shi, Xiaoqing Zheng, Xuanjing Huang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2503.01346 2025-03-07 cs.CL cs.IR 70%

SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

Teng Lin, Yizhang Zhu, Yuyu Luo, Nan Tang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2503.02603 2025-03-06 cs.CL cs.IR 70%

OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing

Yulong Hui, Yihao Liu, Yao Lu, Huanchen Zhang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2502.20596 2025-03-03 cs.CL 70%

Few-Shot, No Problem: Descriptive Continual Relation Extraction

Nguyen Xuan Thanh, Anh Duc Le, Quyen Tran, Thanh-Thien Le, Linh Ngo Van, Thien Huu Nguyen

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments Accepted to AAAI 2025

2502.16860 2025-02-28 cs.CL 70%

LongAttn: Selecting Long-context Training Data via Token-level Attention

Longyun Wu, Dawei Zhu, Guangxiang Zhao, Zhuocheng Yu, Junfeng Ran, Xiangyu Wong, Lin Sun, Sujian Li

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 17 pages, 5 figures

2412.08521 2025-02-28 cs.CL 70%

EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

Yingxin Li, Ye Li, Yuan Meng, Xinzhu Ma, Zihan Geng, Shutao Xia, Zhi Wang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2502.17169 2025-02-25 cs.CL 70%

Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)

Damien Sileo

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2412.12706 2025-02-21 cs.CL 70%

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression

Jiebin Zhang, Dawei Zhu, Yifan Song, Wenhao Wu, Chuqiao Kuang, Xiaoguang Li, Lifeng Shang, Qun Liu, Sujian Li

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 13pages,9 figures

2502.13963 2025-02-20 cs.CL 70%

MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads

Weihao Liu, Ning Wu, Shiping Yang, Wenbiao Ding, Shining Liang, Ming Gong, Dongmei Zhang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 18 pages

2502.13374 2025-02-20 cs.CL 70%

Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor

Barys Liskavets, Shuvendu Roy, Maxim Ushakov, Mark Klibanov, Ali Etemad, Shane Luke

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2502.12462 2025-02-19 cs.CL 70%

Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs

Joon Park, Kyohei Atarashi, Koh Takeuchi, Hisashi Kashima

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments 11 pages, 2 figures

2502.06766 2025-02-13 cs.CL 70%

Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs

Ryan Synk, Monte Hoover, John Kirchenbauer, Neel Jain, Alex Stein, Manli Shu, Josue Melendez Sanchez, Ramani Duraiswami, Tom Goldstein

专题命中长上下文与记忆：LLM(abstract)；language model(abstract)；分类 cs.CL

Comments 9 pages, 9 figures, 2 tables in main body

2502.07488 2025-02-12 cs.LG 70%

Improving Adaptive Moment Optimization via Preconditioner Diagonalization

Son Nguyen, Bo Liu, Lizhang Chen, Qiang Liu

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.LG

Comments 19 pages, 13 figures

2502.01549 2025-02-04 cs.IR cs.AI cs.CV 70%

VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos

Xubin Ren, Lingrui Xu, Long Xia, Shuaiqiang Wang, Dawei Yin, Chao Huang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

2501.18653 2025-02-03 cs.SE cs.AI 70%

Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation

Yanlong Li, Jindong Li, Qi Wang, Menglin Yang, He Kong, Shengsheng Wang

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

2501.15113 2025-01-28 cs.CL 70%

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads

Xingyang He, Jie Liu, Shaowei Chen

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2501.08570 2025-01-28 cs.CL 70%

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms

Kewei Li, Yanwen Kong, Yiping Xu, Jianlin Su, Lan Huang, Ruochi Zhang, Fengfeng Zhou

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

2501.13468 2025-01-24 cs.CV cs.AI 70%

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

Haomiao Xiong, Zongxin Yang, Jiazuo Yu, Yunzhi Zhuge, Lu Zhang, Jiawen Zhu, Huchuan Lu

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Comments Accepted to ICLR 2025. Code is available at https://github.com/hmxiong/StreamChat

2409.02076 2025-01-24 cs.CL 70%

LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs

Yuhao Wu, Ming Shan Hee, Zhiqing Hu, Roy Ka-Wei Lee

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.CL

Comments ICLR 2025; Github: https://github.com/mozhu621/LongGenBench/

2412.19088 2025-01-22 cs.CR cs.AI cs.ET 70%

Integrating Artificial Open Generative Artificial Intelligence into Software Supply Chain Security

Vasileios Alevizos, George A Papakostas, Akebu Simasiku, Dimitra Malliarou, Antonis Messinis, Sabrina Edralin, Clark Xu, Zongliang Yue

专题命中长上下文与记忆：large language model(abstract)；language model(abstract)；分类 cs.AI

Journal ref 2024 5th International Conference on Data Analytics for Business and Industry (ICDABI)

1. 长上下文与记忆 4789 篇

Self-evolving Agents with reflective and memory-augmented abilities

MARS: Memory-Enhanced Agents with Reflective Self-improvement

GazeLLM: Multimodal LLMs incorporating Human Visual Attention

VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning

FReM: A Flexible Reasoning Mechanism for Balancing Quick and Slow Thinking in Long-Context Question Answering

DEMENTIA-PLAN: An Agent-Based Framework for Multi-Knowledge Graph Retrieval-Augmented Generation in Dementia Care

Bootstrap Your Own Context Length

DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels

Encrypted Vector Similarity Computations Using Partially Homomorphic Encryption: Applications and Performance Analysis

NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains

Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling

SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph

OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Query Processing

Few-Shot, No Problem: Descriptive Continual Relation Extraction

LongAttn: Selecting Long-context Training Data via Token-level Attention

EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

Logic Haystacks: Probing LLMs Long-Context Logical Reasoning (Without Easily Identifiable Unrelated Padding)

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression

MuDAF: Long-Context Multi-Document Attention Focusing through Contrastive Learning on Attention Heads

Task-agnostic Prompt Compression with Context-aware Sentence Embedding and Reward-guided Task Descriptor

Emulating Retrieval Augmented Generation via Prompt Engineering for Enhanced Long Context Comprehension in LLMs

Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs

Improving Adaptive Moment Optimization via Preconditioner Diagonalization

VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos

Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads

Information Entropy Invariance: Enhancing Length Extrapolation in Attention Mechanisms

Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge

LongGenBench: Benchmarking Long-Form Generation in Long Context LLMs

Integrating Artificial Open Generative Artificial Intelligence into Software Supply Chain Security