语言大模型 / LLM

Learning to Forget: Sleep-Inspired Memory Consolidation for Resolving Proactive Interference in Large Language Models

学习遗忘：受睡眠启发的记忆巩固用于缓解大语言模型中的前瞻性干扰

Ying Xie

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

AI总结 本文提出SleepGate框架，通过引入学习睡眠周期和三个机制缓解大语言模型中的前瞻性干扰，理论分析显示其将干扰范围从O(n)降至O(log n)。

InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models

InftyThink: 突破大型语言模型长上下文推理的长度限制

Yuchen Yan, Yongliang Shen, Yang Liu, Jin Jiang, Mengdi Zhang, Jian Shao, Yueting Zhuang

机构 * Zhejiang University（浙江大学） ； Meituan Group（美团集团） ； Peking University（北京大学） 纠错

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

AI总结 InftyThink通过迭代推理与中间摘要机制，突破大型语言模型长上下文推理的长度限制，提升推理深度与效率。

Comments ICLR 2026: https://openreview.net/forum?id=T1h5em349L Project Page: https://zju-real.github.io/InftyThink Code: https://github.com/ZJU-REAL/InftyThink

Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

Focus-LIME: 通过基于代理的邻域选择实现长上下文大语言模型的手术解释

Junhao Liu, Haonan Yu, Zhenyu Yan, Xin Zhang

机构 * Key Lab of High Confidence Software Technologies (Peking University)（高可信软件技术重点实验室（北京大学）） ； School of Computer Science, Peking University（计算机学院（北京大学）） 纠错

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

AI总结 Focus-LIME通过基于代理的邻域选择方法，实现长上下文大语言模型的手术级解释，解决了高维特征空间下的归因稀释问题。

Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models

Zer0-Jack: 一种内存高效的基于梯度的对抗方法用于黑盒多模态大语言模型

Tiejin Chen, Kaishen Wang, Hua Wei

机构 * Arizona State University（亚利桑那州立大学） ； University of Maryland（马里兰大学） 纠错

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

AI总结 Zer0-Jack通过零阶优化实现高效黑盒对抗，显著降低内存使用并提升攻击成功率。

Comments Accepted to EACL 2026 Main

On the Failure of Latent State Persistence in Large Language Models

大型语言模型中潜在状态持续性的失效

Jen-tse Huang, Kaiser Sun, Wenxuan Wang, Mark Dredze

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Renmin University of China（中国人民大学） 纠错

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

AI总结 本文揭示大型语言模型在维持持久潜在状态方面的缺陷，通过三个实验展示其在概率分配、概念漂移和变量绑定上的失败，表明LLMs更倾向于反应性求解而非主动规划。

Comments 8 pages, 6 figures, 9 tables

$A^3$: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving

$A^3$：基于注意力的准确KV缓存融合用于快速大语言模型服务

Yuechi Zhou, Yi Su, Jianxin Zhang, Juntao Li, Qingrong Xia, Zhefeng Wang, Xinyu Duan, Baoxing Huai

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

AI总结 $A^3$通过基于注意力的准确KV缓存融合技术，有效降低大语言模型服务的解码延迟和内存开销，提升任务性能。

Discourse Graph Guided Document Translation with Large Language Models

Viet-Thanh Pham, Minghan Wang, Hao-Han Liao, Thuy-Trang Vu

机构 * Department of Data Science & AI, Monash University（数据科学与人工智能系，莫纳什大学） 纠错

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

Backward-Friendly Optimization: Training Large Language Models with Approximate Gradients under Memory Constraints

Jing Yang, Kaitong Cai, Yijia Fan, Yufeng Yang, Keze Wang

机构 * Sun Yat-sen University（中山大学） 纠错

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

Large Language Models as Model Organisms for Human Associative Learning

Camila Kolling, Vy Ai Vo, Mariya Toneva

机构 * Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所） 纠错

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

UltraLLaDA: Scaling the Context Length to 128K for Diffusion Large Language Models

Guangxin He, Shen Nie, Fengqi Zhu, Yuankang Zhao, Tianyi Bai, Ran Yan, Jie Fu, Chongxuan Li, Binhang Yuan

机构 * HKUST（香港科技大学） ； Renmin University of China（中国人民大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Shanghai AI Lab（上海人工智能实验室） 纠错

专题命中 长上下文与记忆 ：large language model(title)；language model(title)；LLM(abstract)；post-training(abstract)

Memory Retrieval and Consolidation in Large Language Models through Function Tokens

Shaohua Zhang, Yuan Lin, Hang Li

机构 * ByteDance Seed（字节跳动种子） 纠错

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

E3RG: Building Explicit Emotion-driven Empathetic Response Generation System with Multimodal Large Language Model

Ronghao Lin, Shuai Shen, Weipeng Hu, Qiaolin He, Aolin Xiong, Li Huang, Haifeng Hu, Yap-peng Tan

机构 * Sun Yat-sen University（中山大学） ； Nanyang Technological University（南洋理工大学） ； Desay SV Automotive Co., Ltd（德赛西威汽车有限公司） ； Pazhou Laboratory（琶洲实验室） 纠错

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

Comments Accepted at ACM MM 2025 Grand Challenge

SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanisms

Yuki Hou, Haruki Tamoto, Qinghua Zhao, Homei Miyashita

机构 * Meiji University（明治大学） ； Kyoto University（京都大学） ； Hefei University（合肥大学） 纠错

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

Comments Accepted to ACL 2025 Findings

Journal ref Findings of the Association for Computational Linguistics: ACL 2025, pages 20422-20436 (2025)

Investigating Context-Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style

Yuepei Li, Kang Zhou, Qiao Qiao, Bach Nguyen, Qing Wang, Qi Li

机构 * Department of Computer Science（计算机科学系） ； Iowa State University（爱荷华州立大学） 纠错

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

Comments This work is published at ACL 2025

CNNSum: Exploring Long-Context Summarization with Large Language Models in Chinese Novels

Lingxiao Wei, He Yan, Xiangju Lu, Junmin Zhu, Jun Wang, Wei Zhang

机构 * East China Normal University（东华大学） ； iQIYI Inc（iQIYI公司） ； Shanghai Innovation Institute（上海创新研究院） 纠错

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

Comments Accepted to ACL 2025 (Findings)

LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration Distillation

Zican Dong, Junyi Li, Jinhao Jiang, Mingyu Xu, Wayne Xin Zhao, Bingning Wang, Weipeng Chen

机构 * Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学人工智能学院） ； Department of Computer Science, National University of Singapore（新加坡国立大学计算机科学系） ； Baichuan Inc.（百川公司） 纠错

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

Comments ACL2025 Main

Mitigate Position Bias in Large Language Models via Scaling a Single Dimension

Yijiong Yu, Huiqiang Jiang, Xufang Luo, Qianhui Wu, Chin-Yew Lin, Dongsheng Li, Yuqing Yang, Yongfeng Huang, Lili Qiu

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

Comments Accepted at Findings of ACL 2025

PSC: Extending Context Window of Large Language Models via Phase Shift Calibration

Wenqiao Zhu, Chao Xu, Lulu Wang, Jun Wu

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

The Mosaic Memory of Large Language Models

Igor Shilov, Matthieu Meeus, Yves-Alexandre de Montjoye

机构 * Imperial College London（伦敦帝国学院） 纠错

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

Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model

Chaochen Gao, Xing Wu, Qi Fu, Songlin Hu

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

Comments ICLR 2025

HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su

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

Comments NeurIPS 2024. Code and data: https://github.com/OSU-NLP-Group/HippoRAG

MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models

Beibei Yu, Tao Shen, Hongbin Na, Ling Chen, Denqi Li

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

Humanlike Cognitive Patterns as Emergent Phenomena in Large Language Models

Zhisheng Tang, Mayank Kejriwal

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

When Context Leads but Parametric Memory Follows in Large Language Models

Yufei Tao, Adam Hiatt, Erik Haake, Antonie J. Jetter, Ameeta Agrawal

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

Comments Accepted by EMNLP 2024 Main Conference

Exploring Context Window of Large Language Models via Decomposed Positional Vectors

Zican Dong, Junyi Li, Xin Men, Wayne Xin Zhao, Bingbing Wang, Zhen Tian, Weipeng Chen, Ji-Rong Wen

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

Comments Accepted by Neurips 2024 as a spotlight

Wave Network: An Ultra-Small Language Model

Xin Zhang, Victor S. Sheng

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

GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models

Shilong Li, Yancheng He, Hangyu Guo, Xingyuan Bu, Ge Bai, Jie Liu, Jiaheng Liu, Xingwei Qu, Yangguang Li, Wanli Ouyang, Wenbo Su, Bo Zheng

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

Comments [EMNLP 2024] The first four authors contributed equally, 29 pages

Explainable cognitive decline detection in free dialogues with a Machine Learning approach based on pre-trained Large Language Models

Francisco de Arriba-Pérez, Silvia García-Méndez, Javier Otero-Mosquera, Francisco J. González-Castaño

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

Journal ref Applied Intelligence, 1-16 (2024)

Personalized Large Language Model Assistant with Evolving Conditional Memory

Ruifeng Yuan, Shichao Sun, Yongqi Li, Zili Wang, Ziqiang Cao, Wenjie Li

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

LayerKV: Optimizing Large Language Model Serving with Layer-wise KV Cache Management

Yi Xiong, Hao Wu, Changxu Shao, Ziqing Wang, Rui Zhang, Yuhong Guo, Junping Zhao, Ke Zhang, Zhenxuan Pan

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

Comments 11 pages, 7 figures, 1 table