语言大模型 / LLM - arXivDaily 专题

2410.03439 2025-04-01 cs.CL 77%

ToolGen: Unified Tool Retrieval and Calling via Generation

Renxi Wang, Xudong Han, Lei Ji, Shu Wang, Timothy Baldwin, Haonan Li

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

Comments ICLR 2025

2411.15556 2025-03-31 cs.CV cs.AI 77%

ReWind: Understanding Long Videos with Instructed Learnable Memory

Anxhelo Diko, Tinghuai Wang, Wassim Swaileh, Shiyan Sun, Ioannis Patras

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

2503.20126 2025-03-27 cs.SE cs.AI cs.PF 77%

Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations

Pooja Rani, Jan-Andrea Bard, June Sallou, Alexander Boll, Timo Kehrer, Alberto Bacchelli

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

2503.17952 2025-03-25 cs.CL 77%

SLIDE: Sliding Localized Information for Document Extraction

Divyansh Singh, Manuel Nunez Martinez, Bonnie J. Dorr, Sonja Schmer Galunder

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

2409.14908 2025-03-24 cs.RO cs.AI 77%

KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems

Zixuan Wang, Bo Yu, Junzhe Zhao, Wenhao Sun, Sai Hou, Shuai Liang, Xing Hu, Yinhe Han, Yiming Gan

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

2503.15754 2025-03-21 cs.CR cs.AI 77%

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

Andy Zhou, Kevin Wu, Francesco Pinto, Zhaorun Chen, Yi Zeng, Yu Yang, Shuang Yang, Sanmi Koyejo, James Zou, Bo Li

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

2503.09819 2025-03-14 cs.CL 77%

Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval

Yuwei Zhang, Jayanth Srinivasa, Gaowen Liu, Jingbo Shang

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

Comments Work in progress

2503.08842 2025-03-13 cs.CL 77%

Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs

Tianyu Sun, Kun Qian, Wenhong Wang

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

2503.07545 2025-03-11 cs.AI cs.DS 77%

Queueing, Predictions, and LLMs: Challenges and Open Problems

Michael Mitzenmacher, Rana Shahout

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

2410.10813 2025-03-06 cs.CL 77%

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, Dong Yu

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

Comments ICLR 2025

2411.05787 2025-03-04 cs.CL 77%

RefreshKV: Updating Small KV Cache During Long-form Generation

Fangyuan Xu, Tanya Goyal, Eunsol Choi

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

2410.04343 2025-03-04 cs.CL 77%

Inference Scaling for Long-Context Retrieval Augmented Generation

Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, Michael Bendersky

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

Comments ICLR 2025

2502.16684 2025-02-25 cs.CL 77%

WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale

Jiaxi Li, Xingxing Zhang, Xun Wang, Xiaolong Huang, Li Dong, Liang Wang, Si-Qing Chen, Wei Lu, Furu Wei

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

2409.08250 2025-02-24 cs.HC cs.AI 77%

OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering

Jiahao Nick Li, Zhuohao Jerry Zhang, Jiaju Ma

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

Comments Paper accepted to the 2025 CHI Conference on Human Factors in Computing Systems (CHI 2025)

2502.12962 2025-02-19 cs.CL 77%

Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing

Xiaoju Ye, Zhichun Wang, Jingyuan Wang

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

Comments 21 pages

2409.19272 2025-02-11 cs.CL 77%

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

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

Comments Accepted at NAACL 2025 Findings

2406.05498 2025-02-06 cs.CR cs.AI 77%

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, Juergen Rahmel

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

Comments Accepted by USENIX Security Symposium 2025. Please cite the conference version of this paper, i.e., "Xunguang Wang, Daoyuan Wu, Zhenlan Ji, Zongjie Li, Pingchuan Ma, Shuai Wang, Yingjiu Li, Yang Liu, Ning Liu, and Juergen Rahmel. SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner. In Proc. USENIX Security, 2025."

2402.10178 2025-01-22 cs.CL 77%

TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation

Yaoxiang Wang, Zhiyong Wu, Junfeng Yao, Jinsong Su

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

Comments Accepted by Neural Networks

2412.09237 2024-12-16 cs.AI 77%

LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation

Yijun Liu, Wu Liu, Xiaoyan Gu, Yong Rui, Xiaodong He, Yongdong Zhang

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

2412.07246 2024-12-11 cs.CL cs.DB 77%

Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs without Real Data Replay

Ruiheng Liu, Jinyu Zhang, Yanqi Song, Yu Zhang, Bailong Yang

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

2411.13476 2024-11-27 cs.CL 77%

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training

Haonan Wang, Qian Liu, Chao Du, Tongyao Zhu, Cunxiao Du, Kenji Kawaguchi, Tianyu Pang

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

2311.04742 2024-11-26 cs.CL q-bio.NC 77%

Large-scale study of human memory for meaningful narratives

Antonios Georgiou, Tankut Can, Mikhail Katkov, Misha Tsodyks

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

Comments 45 pages, significant revision

2410.05586 2024-11-12 cs.CV cs.AI 77%

TeaserGen: Generating Teasers for Long Documentaries

Weihan Xu, Paul Pu Liang, Haven Kim, Julian McAuley, Taylor Berg-Kirkpatrick, Hao-Wen Dong

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

2410.20334 2024-11-11 cs.CL cs.SD eess.AS 77%

Improving Speech-based Emotion Recognition with Contextual Utterance Analysis and LLMs

Enshi Zhang, Christian Poellabauer

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

2410.18050 2024-11-04 cs.CL 77%

LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering

Qingfei Zhao, Ruobing Wang, Yukuo Cen, Daren Zha, Shicheng Tan, Yuxiao Dong, Jie Tang

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

Comments EMNLP 2024 Main, Final

2410.17781 2024-10-24 cs.AI 77%

Evaluating Explanations Through LLMs: Beyond Traditional User Studies

Francesco Bombassei De Bona, Gabriele Dominici, Tim Miller, Marc Langheinrich, Martin Gjoreski

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

2406.19598 2024-10-18 cs.CL 77%

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness

Hongzhan Lin, Ang Lv, Yuhan Chen, Chen Zhu, Yang Song, Hengshu Zhu, Rui Yan

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

Comments Accepted by Neurips2024

2409.18006 2024-10-15 cs.CL 77%

Evaluating Multilingual Long-Context Models for Retrieval and Reasoning

Ameeta Agrawal, Andy Dang, Sina Bagheri Nezhad, Rhitabrat Pokharel, Russell Scheinberg

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

Comments To appear at MRL 2024

2407.13505 2024-10-14 cs.RO cs.AI 77%

Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation

Hassan Ali, Philipp Allgeuer, Carlo Mazzola, Giulia Belgiovine, Burak Can Kaplan, Lukáš Gajdošech, Stefan Wermter

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

2410.03227 2024-10-07 cs.CL 77%

ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering

Huayang Li, Pat Verga, Priyanka Sen, Bowen Yang, Vijay Viswanathan, Patrick Lewis, Taro Watanabe, Yixuan Su

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

1. 长上下文与记忆 4779 篇

ToolGen: Unified Tool Retrieval and Calling via Generation

ReWind: Understanding Long Videos with Instructed Learnable Memory

Can We Make Code Green? Understanding Trade-Offs in LLMs vs. Human Code Optimizations

SLIDE: Sliding Localized Information for Document Extraction

KARMA: Augmenting Embodied AI Agents with Long-and-short Term Memory Systems

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval

Contrastive Speaker-Aware Learning for Multi-party Dialogue Generation with LLMs

Queueing, Predictions, and LLMs: Challenges and Open Problems

LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory

RefreshKV: Updating Small KV Cache During Long-form Generation

Inference Scaling for Long-Context Retrieval Augmented Generation

WildLong: Synthesizing Realistic Long-Context Instruction Data at Scale

OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering

Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing

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

SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner

TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation

LMAgent: A Large-scale Multimodal Agents Society for Multi-user Simulation

Filling Memory Gaps: Enhancing Continual Semantic Parsing via SQL Syntax Variance-Guided LLMs without Real Data Replay

When Precision Meets Position: BFloat16 Breaks Down RoPE in Long-Context Training

Large-scale study of human memory for meaningful narratives

TeaserGen: Generating Teasers for Long Documentaries

Improving Speech-based Emotion Recognition with Contextual Utterance Analysis and LLMs

LongRAG: A Dual-Perspective Retrieval-Augmented Generation Paradigm for Long-Context Question Answering

Evaluating Explanations Through LLMs: Beyond Traditional User Studies

Mixture of In-Context Experts Enhance LLMs' Long Context Awareness

Evaluating Multilingual Long-Context Models for Retrieval and Reasoning

Robots Can Multitask Too: Integrating a Memory Architecture and LLMs for Enhanced Cross-Task Robot Action Generation

ALR$^2$: A Retrieve-then-Reason Framework for Long-context Question Answering