语言大模型 / LLM

Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models

超越前缀：基于图记忆的交叉注意力用于大型语言模型的知识图谱补全

Ruitong Liu, Boxu Lin, Peize Li, Siyuan Li, Yunjia Wu, Te Sun, Chaohan Wu

机构 * Peking University（北京大学） ； Dalian University of Technology（大连理工大学） ； King’s College London（伦敦国王学院） ； Peng Cheng Laboratory（鹏城实验室） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 本文提出图记忆调优方法，通过深度交叉注意力机制提升大型语言模型在知识图谱补全任务中的表现。

TFL: Targeted Bit-Flip Attack on Large Language Model

TFL：针对大语言模型的定向位翻转攻击

Jingkai Guo, Chaitali Chakrabarti, Deliang Fan

机构 * School of Electrical, Computer and Energy Engineering（电气、计算机与能源工程学院） ； Arizona State University（亚利桑那州立大学） 纠错

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

AI总结 TFL是一种新型定向位翻转攻击框架，通过精确操控LLM输出并减少对无关输入的影响，提升攻击的隐蔽性和针对性。

Comments 13 pages, 11 figures. Preprint

Internalizing Meta-Experience into Memory for Guided Reinforcement Learning in Large Language Models

将元经验内化到记忆中以指导大语言模型的强化学习

Shiting Huang, Zecheng Li, Yu Zeng, Qingnan Ren, Zhen Fang, Qisheng Su, Kou Shi, Lin Chen, Zehui Chen, Feng Zhao

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

AI总结 通过将元经验内化到记忆中，MEL提升了大语言模型的强化学习效果，实现了更有效的知识重用和推理能力增强。

G-MemLLM: Gated Latent Memory Augmentation for Long-Context Reasoning in Large Language Models

G-MemLLM：基于门控潜在记忆增强的长上下文推理大语言模型

Xun Xu

机构 * Department of Computer Science（计算机科学系） ； Fudan University（复旦大学） 纠错

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

AI总结 G-MemLLM通过引入门控潜在记忆库，提升大语言模型在长上下文推理中的表现，显著增强多跳推理和关系精度。

MemoryRewardBench: Benchmarking Reward Models for Long-Term Memory Management in Large Language Models

MemoryRewardBench: 评估大型语言模型中长期记忆管理的奖励模型基准

Zecheng Tang, Baibei Ji, Ruoxi Sun, Haitian Wang, WangJie You, Zhang Yijun, Wenpeng Zhu, Ji Qi, Juntao Li, Min Zhang

机构 * LCM Laboratory（LCM实验室） ； China Mobile (Suzhou)（中国移动（苏州）） 纠错

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

AI总结 MemoryRewardBench通过系统评估奖励模型在长序列内存管理中的表现，揭示了不同模型在长期记忆处理中的能力差异与局限性。

LLM-as-RNN: A Recurrent Language Model for Memory Updates and Sequence Prediction

LLM-as-RNN: 一种用于内存更新和序列预测的循环语言模型

Yuxing Lu, J. Ben Tamo, Weichen Zhao, Nan Sun, Yishan Zhong, Wenqi Shi, Jinzhuo Wang, May D. Wang

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Peking University（北京大学） ； Shandong University（山东大学） ； Huazhong University of Science and Technology（华中科技大学） ； UT Southwestern Medical Center（西南医学中心） 纠错

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

AI总结 LLM-as-RNN通过将冻结的LLM转化为循环预测器，利用自然语言记忆实现在线学习，有效提升序列预测精度并生成可解释的学习轨迹。

Comments 17 pages, 5 figures, 6 tables

Memory Bank Compression for Continual Adaptation of Large Language Models

基于记忆库压缩的大型语言模型持续适应

Thomas Katraouras, Dimitrios Rafailidis

机构 * University of Thessaly（塞萨洛尼基大学） 纠错

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

AI总结 MBC通过代码本优化策略和键值低秩适应，实现大型语言模型持续适应中的记忆库压缩，有效减少内存占用并保持高准确性。

Comments Accepted to the 41st ACM/SIGAPP Symposium on Applied Computing (SAC '26)

When Many-Shot Prompting Fails: An Empirical Study of LLM Code Translation

当多示例提示失效：对LLM代码翻译的实证研究

Amirkia Rafiei Oskooei, Kaan Baturalp Cosdan, Husamettin Isiktas, Mehmet S. Aktas

机构 * Yildiz Technical University, Department of Computer Engineering（Yildiz技术大学计算机工程系） 纠错

专题命中 长上下文与记忆 ：prompting(title,abstract)；LLM(title)；large language model(abstract)；language model(abstract)

AI总结 本研究发现代码翻译中少量精心挑选的示例比大量示例更有效，挑战了ICL中'更多更好'的普遍假设。

Comments Accepted to ICSE 2026 (RECODE workshop)

Towards a Psychology of Machines: Large Language Models Predict Human Memory

迈向机器的心理学：大型语言模型预测人类记忆

Markus Huff, Elanur Ulakçı

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

AI总结 本研究发现大型语言模型能有效预测人类记忆表现，揭示了LLMs在模拟人类认知方面的潜力，提出机器心理学作为新研究领域。

Comments 34 pages, 3 figures, 2 tables

Journal ref PeerJ Comput.Sci. 11 (2025) e3324

LGM: Enhancing Large Language Models with Conceptual Meta-Relations and Iterative Retrieval

Wenchang Lei, Ping Zou, Yue Wang, Feng Sun, Lei Zhao

机构 * Philisense（哲思科技） 纠错

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

Comments 30 pages, 5 figures

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

Jiaqi Cao, Jiarui Wang, Rubin Wei, Qipeng Guo, Kai Chen, Bowen Zhou, Zhouhan Lin

机构 * LUMIA Lab（LUMIA实验室） ； School of Artificial Intelligence（人工智能学院） ； Shanghai Jiao Tong University（上海交通大学） ； Shanghai AI Laboratory（上海人工智能实验室） ； Tsinghua University（清华大学） ； SJTU Paris Elite Institute of Technology（上海交通大学巴黎精英技术学院） 纠错

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

PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Process

Xinliang Frederick Zhang, Nick Beauchamp, Lu Wang

机构 * Computer Science and Engineering, University of Michigan, Ann Arbor, MI（计算机科学与工程系，密歇根大学，安娜堡分校） ； Department of Political Science, Northeastern University, Boston, MA（政治学系，东北大学，波士顿分校） 纠错

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

Comments EMNLP'25 Main

Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models

Qingyue Wang, Yanhe Fu, Yanan Cao, Shuai Wang, Zhiliang Tian, Liang Ding

机构 * the Department of Computer Science and Engineering, Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系） ； the institute of information engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； the College of Computer, National University of Defense Technology（国防科技大学计算机学院） ； the University of Sydney（悉尼大学） 纠错

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

Comments This paper has been accepted by Neurocomputing

How Overconfidence in Initial Choices and Underconfidence Under Criticism Modulate Change of Mind in Large Language Models

Dharshan Kumaran, Stephen M Fleming, Larisa Markeeva, Joe Heyward, Andrea Banino, Mrinal Mathur, Razvan Pascanu, Simon Osindero, Benedetto de Martino, Petar Velickovic, Viorica Patraucean

机构 * Google DeepMind（谷歌DeepMind） ； Google Research（谷歌研究） ； University College London（伦敦大学学院） 纠错

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

Comments 41 pages

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation

Samuel Holt, Max Ruiz Luyten, Mihaela van der Schaar

机构 * University of Cambridge（剑桥大学） 纠错

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

Comments Published in The Twelfth International Conference on Learning Representations (ICLR), 2024. Copyright 2023 by the author(s)

From RAG to Memory: Non-Parametric Continual Learning for Large Language Models

Bernal Jiménez Gutiérrez, Yiheng Shu, Weijian Qi, Sizhe Zhou, Yu Su

机构 * The Ohio State University, Columbus, OH, USA（俄亥俄州立大学） ； University of Illinois Urbana-Champaign, IL, USA（伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments ICML 2025. Code and data are available at: https://github.com/OSU-NLP-Group/HippoRAG

An Empirical Study on Prompt Compression for Large Language Models

Zheng Zhang, Jinyi Li, Yihuai Lan, Xiang Wang, Hao Wang

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； South China University of Technology（华南理工大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

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

Comments Accepted by Building Trust Workshop at ICLR 2025

Cognitive Memory in Large Language Models

Lianlei Shan, Shixian Luo, Zezhou Zhu, Yu Yuan, Yong Wu

机构 * Li Auto（利亚 Auto） 纠错

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

Comments 37 pages, 9 figures

CMAT: A Multi-Agent Collaboration Tuning Framework for Enhancing Small Language Models

Xuechen Liang, Yangfan He, Meiling Tao, Yinghui Xia, Jianhui Wang, Tianyu Shi, Jun Wang, JingSong Yang

专题命中 长上下文与记忆 ：language model(title,abstract)；small language model(title)；large language model(abstract)；language agent(abstract)

PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System

Yintao He, Haiyu Mao, Christina Giannoula, Mohammad Sadrosadati, Juan Gómez-Luna, Huawei Li, Xiaowei Li, Ying Wang, Onur Mutlu

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

Comments To appear in ASPLOS 2025

LongSafety: Evaluating Long-Context Safety of Large Language Models

Yida Lu, Jiale Cheng, Zhexin Zhang, Shiyao Cui, Cunxiang Wang, Xiaotao Gu, Yuxiao Dong, Jie Tang, Hongning Wang, Minlie Huang

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

Compositional Hardness of Code in Large Language Models -- A Probabilistic Perspective

Yotam Wolf, Binyamin Rothberg, Dorin Shteyman, Amnon Shashua

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

Large Language Models Can Self-Improve in Long-context Reasoning

Siheng Li, Cheng Yang, Zesen Cheng, Lemao Liu, Mo Yu, Yujiu Yang, Wai Lam

专题命中 长上下文与记忆 ：large language model(title,abstract)；language model(title,abstract)；preference optimization(abstract)；分类 cs.CL、cs.AI

Comments Project Page: https://github.com/SihengLi99/SEALONG

StockTime: A Time Series Specialized Large Language Model Architecture for Stock Price Prediction

Shengkun Wang, Taoran Ji, Linhan Wang, Yanshen Sun, Shang-Ching Liu, Amit Kumar, Chang-Tien Lu

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

Resonance RoPE: Improving Context Length Generalization of Large Language Models

Suyuchen Wang, Ivan Kobyzev, Peng Lu, Mehdi Rezagholizadeh, Bang Liu

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

Comments 13 pages, 4 figures, accepted at ACL 2024 Findings

Journal ref https://aclanthology.org/2024.findings-acl.32

Larimar: Large Language Models with Episodic Memory Control

Payel Das, Subhajit Chaudhury, Elliot Nelson, Igor Melnyk, Sarath Swaminathan, Sihui Dai, Aurélie Lozano, Georgios Kollias, Vijil Chenthamarakshan, Jiří, Navrátil, Soham Dan, Pin-Yu Chen

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

Comments ICML 2024

HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model

Mengkang Hu, Tianxing Chen, Qiguang Chen, Yao Mu, Wenqi Shao, Ping Luo

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

Comments Project Page: https://github.com/HiAgent2024/HiAgent

Conversational AI Powered by Large Language Models Amplifies False Memories in Witness Interviews

Samantha Chan, Pat Pataranutaporn, Aditya Suri, Wazeer Zulfikar, Pattie Maes, Elizabeth F. Loftus

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

Empowering Private Tutoring by Chaining Large Language Models

Yulin Chen, Ning Ding, Hai-Tao Zheng, Zhiyuan Liu, Maosong Sun, Bowen Zhou

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

Evaluating Quantized Large Language Models

Shiyao Li, Xuefei Ning, Luning Wang, Tengxuan Liu, Xiangsheng Shi, Shengen Yan, Guohao Dai, Huazhong Yang, Yu Wang

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