语言大模型 / LLM

Large Language Models are Biased Reinforcement Learners

William M. Hayes, Nicolas Yax, Stefano Palminteri

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models

Yuchen Hu, Chen Chen, Chengwei Qin, Qiushi Zhu, Eng Siong Chng, Ruizhe Li

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 14 pages, Accepted by ACL 2024

Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing

Le Yan, Zhen Qin, Honglei Zhuang, Rolf Jagerman, Xuanhui Wang, Michael Bendersky, Harrie Oosterhuis

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

zrLLM: Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models

Zifeng Ding, Heling Cai, Jingpei Wu, Yunpu Ma, Ruotong Liao, Bo Xiong, Volker Tresp

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to NAACL 2024 main conference

Calibrating Large Language Models Using Their Generations Only

Dennis Ulmer, Martin Gubri, Hwaran Lee, Sangdoo Yun, Seong Joon Oh

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Relative Value Biases in Large Language Models

William M. Hayes, Nicolas Yax, Stefano Palminteri

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；prompting(abstract)；分类 cs.CL、cs.AI、cs.LG

Wordflow: Social Prompt Engineering for Large Language Models

Zijie J. Wang, Aishwarya Chakravarthy, David Munechika, Duen Horng Chau

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments 8 pages, 7 figures. Wordflow is available at: https://poloclub.github.io/wordflow. The code is available at: https://github.com/poloclub/wordflow/. For a demo video, see: https://youtu.be/3dOcVuofGVo

Evolutionary Multi-Objective Optimization of Large Language Model Prompts for Balancing Sentiments

Jill Baumann, Oliver Kramer

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted in EvoApps at EvoStar 2024

Large Language Models aren't all that you need

Kiran Voderhobli Holla, Chaithanya Kumar, Aryan Singh

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

D-Bot: Database Diagnosis System using Large Language Models

Xuanhe Zhou, Guoliang Li, Zhaoyan Sun, Zhiyuan Liu, Weize Chen, Jianming Wu, Jiesi Liu, Ruohang Feng, Guoyang Zeng

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

Jiaqi Xue, Mengxin Zheng, Ting Hua, Yilin Shen, Yepeng Liu, Ladislau Boloni, Qian Lou

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted by NeurIPS'23

Forgetful Large Language Models: Lessons Learned from Using LLMs in Robot Programming

Juo-Tung Chen, Chien-Ming Huang

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；prompting(abstract)

Comments 9 pages ,8 figures, accepted by the AAAI 2023 Fall Symposium Series

Large Language Models in Analyzing Crash Narratives -- A Comparative Study of ChatGPT, BARD and GPT-4

Maroa Mumtarin, Md Samiullah Chowdhury, Jonathan Wood

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?

Xin Xu, Yuqi Zhu, Xiaohan Wang, Ningyu Zhang

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments SustaiNLP Workshop@ACL 2023

Taming AI Bots: Controllability of Neural States in Large Language Models

Stefano Soatto, Paulo Tabuada, Pratik Chaudhari, Tian Yu Liu

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments TLDR: AI Bots are stochastic dynamical systems whose mental state can be controlled by both the user and the designer. The space of meanings, defined as equivalence classes of sentences, is learned during fine-tuning with human supervision, and safeguarding can be designed into the bot by establishing controls both at its input and output

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, Jifeng Dai

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；foundation model(abstract)

Comments Technical Report

Large Language Models Are Human-Level Prompt Engineers

Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, Jimmy Ba

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Improving Language Model Prompting in Support of Semi-autonomous Task Learning

James R. Kirk, Robert E. Wray, Peter Lindes, John E. Laird

专题命中 其他LLM ：language model(title,abstract)；prompting(title,abstract)；LLM(abstract)；分类 cs.CL、cs.AI、cs.LG

Comments Accepted to ACS 2022 (poster)

Improving Multimodal Large Language Models Using Continual Learning

Shikhar Srivastava, Md Yousuf Harun, Robik Shrestha, Christopher Kanan

机构 * University of Rochester（罗切斯特大学） ； Rochester Institute of Technology（罗切斯特理工学院） 纠错

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract)；分类 cs.CL、cs.LG

Comments CoLLAs 2025 and Scalable Continual Learning for Lifelong Foundation Models, NeurIPS 2024

The Only Way is Ethics: A Guide to Ethical Research with Large Language Models

Eddie L. Ungless, Nikolas Vitsakis, Zeerak Talat, James Garforth, Björn Ross, Arno Onken, Atoosa Kasirzadeh, Alexandra Birch

专题命中 其他LLM ：large language model(title,abstract)；language model(title,abstract)；LLM(abstract,comments)；分类 cs.CL、cs.AI

Comments Accepted to COLING '25. This paper is the condensed pocket guide to accompany our full LLM Ethics Whitepaper, available at arXiv:2410.19812, and at https://github.com/MxEddie/Ethics-Whitepaper for suggested revisions

LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents

LEDGER：用于审计大语言模型智能体的从主张到证据的追踪图

Daehong Kim, Haichao Miao, Shusen Liu

专题命中 其他LLM ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 针对LLM智能体输出审计瓶颈，提出LEDGER系统构建分层追踪图，通过分组节点、添加语义边等实现以证据为中心的审计，揭示工作流决策等关键信息。

Breaking and Defending LLM-Powered Social Media Bot Detection Systems

突破与防御：基于大语言模型的社交媒体机器人检测系统

Nof Orenstein, Yoni Birman

机构 * Reichman University（莱希曼大学） 纠错

专题命中 其他LLM ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 本研究针对基于大语言模型的社交媒体机器人检测系统，提出两种新型对抗攻击策略使其准确率降48%，并开发多LLM防御框架LSABRE，在强自适应对抗下仍维持86%准确率，相关方法可推广至其他LLM网络安全系统。

Comments Accepted at ACISP 2026 (Australasian Conference on Information Security and Privacy). Also accepted as a poster at IEEE Symposium on Security and Privacy (S&P) 2026. Published in Pragmatic Cybersecurity 2026, 1(2), 10, https://doi.org/10.53941/pc.2026.100010. 19 pages, 11 figures

Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents

超越手工安全：面向大语言模型智能体的自演化防御

Jiajun Ruan, Peiyang Li, Yukun Chen, Fengting Li, Chao Feng

专题命中 其他LLM ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 针对 LLM 智能体的安全威胁，提出自演化运行时防御框架 HARD，将防御开发从人工工程转为自主演化，在保留任务效用的同时提升了安全性能。

Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols

纠正与腐败：LLM协议中错误流动的双速率视角

Fernando Reitich

机构 * Imens, LLC（Imens公司） 纠错

专题命中 其他LLM ：LLM(title,title_cn)；large language model(abstract)；language model(abstract)；分类 cs.LG

AI总结 本文提出双速率方法评估LLM协议步骤，区分纠正与腐败，通过实验验证其在不同任务中的有效性。

Comments 16 pages main paper, 19 pages supplementary material included as ancillary file. Major revision with substantially reorganized and streamlined presentation; expanded held-out prediction, population-composition, input-sensitivity, and composition analyses; includes an MBPP corruption audit and updated related work

Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models

说服倾向与顺从倾向预测人类及语言模型的群体决策

Wenwen He, Wenke Huang, Wei Yang Bryan Lim, Dacheng Tao

机构 * College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院） 纠错

专题命中 其他LLM ：LLM(summary_cn,abstract)；language model(title,abstract)；large language model(abstract)；分类 cs.AI

AI总结 该研究引入DecisionQE框架，以狼人杀为测试平台，发现顺从倾向强的LLM在群体决策中合作优势更稳定，且顺从兼具支持合作与提升对抗角色隐藏能力的双重效应，为LLM安全评估提供了新视角。

Autonomy Reshapes How Personalization Affects Privacy Concerns and Trust in LLM Agents

自主性重塑个性化对隐私担忧和对LLM代理信任的影响

Zhiping Zhang, Yi Evie Zhang, Freda Shi, Tianshi Li

机构 * Northeastern University（东北大学） ； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； University of Waterloo（滑铁卢大学） 纠错

专题命中 其他LLM ：LLM(title,title_cn)；分类 cs.AI

AI总结 研究探讨了LLM代理自主性如何影响个性化对用户隐私担忧和信任的影响，发现风险驱动的自主性可缓解个性化带来的负面影响。

Comments Accepted to COLM 2026

PICopilot: An LLM-based Agentic Framework for Assisting Photonic Integrated Circuit Design via Script Generation

PICopilot：一种基于大语言模型的智能体框架，通过脚本生成辅助光子集成芯片设计

Xiaohan Jiang, Zeyu Li, Wei Zhang, Jiang Xu

专题命中 其他LLM ：LLM(title,summary_cn)；large language model(abstract)；language model(abstract)；分类 cs.AI

AI总结 PICopilot是首个基于LLM的智能体框架，通过带反馈机制的多智能体架构与专用RAG流程，成功完成全部48项PIC脚本任务，性能优于其他LLM方法及通用RAG的GPT-5。

Comments 9 pages, 6 figures

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

AgentAntibody：一种用于防御大语言模型（LLM）智能体提示注入的自适应免疫系统

Shihao Weng, Yang Feng, Xiaofei Xie, Jiongchi Yu

专题命中 其他LLM ：LLM(title,title_cn)；分类 cs.AI

AI总结 针对LLM智能体的提示注入威胁，受自适应免疫启发提出AgentAntibody，通过持久抗体库识别威胁并进化增强防御，实验显示其在防有害行为同时保留合法任务完成上优于现有防御。

Comments 7 pages

Collab-REC: An LLM-based Agentic Framework for Balancing Recommendations in Tourism

Collab-REC：一种基于LLM的代理框架，用于平衡旅游推荐

Ashmi Banerjee, Adithi Satish, Fitri Nur Aisyah, Wolfgang Wörndl, Yashar Deldjoo

机构 * Technical University of Munich（慕尼黑技术大学） ； Polytechnic University of Bari（巴里理工大学） 纠错

专题命中 其他LLM ：LLM(title,title_cn)；分类 cs.AI

AI总结 提出一种多代理框架Collab-REC，通过三个LLM代理（个性化、流行度、可持续性）生成城市建议，并由非LLM调节器迭代优化，以缓解流行度偏差并提高推荐多样性。

Comments Accepted at ACM Transactions on Recommender Systems (TORS), August 2026

Journal ref ACM Transactions on Recommender Systems (TORS), 2026

Will the Agent Recuse, and Will It Stop? Measuring LLM-Agent Compliance with In-Band Governance Signals at the Access Door and Mid-Flight

智能体会自行回避吗？测量LLM智能体对带内拒绝访问信号的遵从性

Thamilvendhan Munirathinam

机构 * University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 其他LLM ：LLM(title,title_cn)；分类 cs.AI

AI总结 提出一种轻量级带内拒绝信号（Recuse Signal），通过实验测量LLM智能体是否自愿遵从该信号，发现信号能有效诱导回避，但高级模型在操作员授权下可能忽略。

Comments v4: adds Experiment 4 (cross-vendor mid-task halt; measured harness-enforcement backstop). 15 pages, 2 figures