This study analyzes changes in the attention mechanisms of large language models (LLMs) when used to understand natural conversations between humans (human-human). We analyze three use cases of LLMs: interactions over web content, code, and mathematical texts. By analyzing attention distance, dispersion, and interdependency across these domains, we highlight the unique challenges posed by conversational data. Notably, conversations require nuanced handling of long-term contextual relationships and exhibit higher complexity through their attention patterns. Our findings reveal that while language models exhibit domain-specific attention behaviors, there is a significant gap in their ability to specialize in human conversations. Through detailed attention entropy analysis and t-SNE visualizations, we demonstrate the need for models trained with a diverse array of high-quality conversational data to enhance understanding and generation of human-like dialogue. This research highlights the importance of domain specialization in language models and suggests pathways for future advancement in modeling human conversational nuances.
Old Habits Die Hard: How Conversational History Geometrically Traps LLMs
Technion - Israel Institute of Technology（技术ion-以色列理工学院）；University of Oxford（牛津大学）；University of Zagreb, FER（Zagreb大学，FER）；Kempner Institute, Harvard University（Kempner研究所，哈佛大学）；University of Edinburgh（爱丁堡大学）
A Scoping Review of the Ethical Perspectives on Anthropomorphising Large Language Model-Based Conversational Agents
Institute of Biomedical Ethics and History of Medicine, University of Zürich（苏黎世大学生物医学伦理与医学史研究所）；Dalle Molle Institute for Artificial Intelligence (IDSIA), SUPSI（瑞士SUPSI人工智能研究所）；ETH Zürich（苏黎世联邦理工学院）；Institute for Implementation Science in Health Care, University of Zürich（苏黎世大学医疗实施科学研究所）；Department of Management, Technology and Economics, ETH Zürich（苏黎世联邦理工学院管理、技术与经济系）；Dipartimento Tecnologie Innovative, SUPSI（SUPSI创新技术系）；Management in Networked and Digital Societies (MINDS) Department, Kozminski University（科兹明斯基大学网络化与数字化社会管理系）
Real-time Speech Summarization for Medical Conversations
University of Toronto（多伦多大学）；University Health Network（大学健康网络）；College of William and Mary（威廉玛丽学院）；University of Cincinnati（辛辛那提大学）；Indiana State University（印第安纳州立大学）；FPT Software AI Center（FPT软件人工智能中心）
A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations
Microsoft Research Asia（微软亚洲研究院）；Hong Kong University of Science and Technology（香港科技大学）；Peking University（北京大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Deutsche Welle（德国之声）；Universitat Politecnica de Valencia（瓦伦西亚理工大学）；ABC News（美国广播公司新闻部）；Bonn-Aachen International Center for Information Technology (b-it), University of Bonn（波恩大学波恩-亚琛国际信息技术中心）；The Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔机器学习与人工智能研究所）
OncoGPT: A Medical Conversational Model Tailored with Oncology Domain Expertise on a Large Language Model Meta-AI (LLaMA)
Shenzhen Kanghua Juntai Biotech Co. Ltd.（深圳康华君泰生物科技有限公司）；University of California, Davis（加利福尼亚大学戴维斯分校）；The First Affiliated Hospital of Jinan University（暨南大学附属第一医院）
EventChat: Implementation and user-centric evaluation of a large language model-driven conversational recommender system for exploring leisure events in an SME context
Swiss Federal Institute of Technology, Zurich（苏黎世联邦理工学院）
Dialogue Quality and Emotion Annotations for Customer Support Conversations
INESC-ID（INESC-ID（葡萄牙国家系统与计算机工程研究所））；Instituto Superior Técnico, University of Lisbon（里斯本大学高等技术学院）；Faculdade de Letras, University of Lisbon（里斯本大学文学院）；Unbabel（Unbabel公司）；Carnegie Mellon University（卡内基梅隆大学）；Phrase（Phrase公司）
GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing
Drexel University（德雷塞尔大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）；Brown University（布朗大学）；UT Austin（德克萨斯大学奥斯汀分校）；New Jersey Institute of Technology（新泽西理工学院）；University of Pennsylvania（宾夕法尼亚大学）
Evaluating LLMs on Generating Age-Appropriate Child-Like Conversations
Department of Holistic Systems, SimulaMet（整体系统系，SimulaMet）；Department of Computer Science, Oslo Metropolitan University（计算机科学系，奥斯陆 Metropolitan 大学）；Department of Behavioural Sciences, Oslo Metropolitan University（行为科学系，奥斯陆 Metropolitan 大学）；Department of Psychology, Harvard University（心理学系，哈佛大学）；Department of Informatics, University of Oslo（信息学系，奥斯陆大学）；Norwegian Computing Center（挪威计算中心）
Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Models
Chinese University of Hong Kong（香港中文大学）；National University of Singapore（新加坡国立大学）；Singapore Management University（新加坡管理大学）；Hong Kong Baptist University（香港浸会大学）；Huazhong University of Science and Technology（华中科技大学）
DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations
National Computer System Engineering Research Institute of China（中国国家计算机系统工程研究所）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
Baidu Research - Institue of Deep Learning（百度研究院 - 深度学习研究所）；National Engineering Laboratory for Deep Learning Technology and Applications（深度学习技术及应用国家工程实验室）
Dagstuhl Perspectives Workshop 24352 -- Conversational Agents: A Framework for Evaluation (CAFE): Manifesto
University of Salzburg（萨尔茨堡大学）；Hong Kong Baptist University（香港 Baptist 大学）；University of Padua（帕多瓦大学）；Universität Duisburg-Essen（杜伊斯堡- Essen 大学）；TU Delft（代尔夫特理工大学）；TH Köln（科隆应用技术大学）；Georgetown University（乔治城大学）；University of Tsukuba（筑波大学）；Silo AI；Bauhaus-Universität Weimar（魏玛包豪斯大学）；Clemson University（克莱姆斯大学）；University College London（伦敦大学学院）；imec-SMIT；University of Antwerp（安特卫普大学）；University of Twente（埃因霍温理工大学）；RMIT University（皇家理工学院）；University of Toronto（多伦多大学）；TU Eindhoven & JADS（埃因霍温理工大学及JADS）
