The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG. In recent years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game.
GASCADE: Grouped Summarization of Adverse Drug Event for Enhanced Cancer Pharmacovigilance
Department of Computer Science & Engineering, Indian Institute of Technology Patna（印度理工学院帕纳布分校计算机科学与工程系）；Indira Gandhi Institute of Medical Sciences, Patna（英伽丁医学科学学院）
APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation
Tianjin University（天津大学）；Zhejiang University（浙江大学）；North University of China（北方工业大学）；Institute of Science Tokyo（东京科学研究所）；The Hong Kong Polytechnic University（香港理工大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江）区块链与数据安全研究院）
Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
State Key Laboratory for Novel Software Technology, Nanjing University, China（新型软件技术国家重点实验室，南京大学）；National Institute of Healthcare Data Science, Nanjing University, China（健康数据科学国家研究院，南京大学）
Shandong University（山东大学）；Peking University（北京大学）；Ant Group（蚂蚁集团）；Renmin University of China（中国人民大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）
Review summarization is a non-trivial task that aims to summarize the main idea of the product review in the E-commerce website. Different from the document summary which only needs to focus on the main facts described in the document, review summarization should not only summarize the main aspects mentioned in the review but also reflect the personal style of the review author. Although existing review summarization methods have incorporated the historical reviews of both customer and product, they usually simply concatenate and indiscriminately model this two heterogeneous information into a…
Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization
Idiap Research Institute（Idiap 研究所）；University of Zurich（苏黎世大学）；The Ohio State University（俄亥俄州立大学）；Université de Toulon, Aix Marseille Univ, LIS, CNRS（土伦大学，艾克斯-马赛大学，计算机与系统实验室，法国国家科学研究中心）；Stenograf；Johns Hopkins University Bloomberg School of Public Health（约翰·霍普金斯大学布隆伯格公共卫生学院）；Colorado School of Mines（科罗拉多矿业学院）；Allegheny Health Network（阿勒格尼健康网络）；University of Pittsburgh Medical Center（匹兹堡大学医学中心）；ILLS, CNRS（ILLS，法国国家科学研究中心）；Solventum；Carnegie Mellon University（卡内基梅隆大学）
Institute for Infocomm Research, A*STAR, Singapore（资讯通信研究院（A*STAR），新加坡）
In this paper, we propose a controllable neural generation framework that can flexibly guide dialogue summarization with personal named entity planning. The conditional sequences are modulated to decide what types of information or what perspective to focus on when forming summaries to tackle the under-constrained problem in summarization tasks. This framework supports two types of use cases: (1) Comprehensive Perspective, which is a general-purpose case with no user-preference specified, considering summary points from all conversational interlocutors and all mentioned persons; (2) Focus Pers…
Department of Computer Science, University of Illinois, Chicago, IL, 60607, USA（伊利诺伊大学芝加哥分校计算机科学系）；Indian Institute of Technology, Varanasi, India（印度班加罗尔理工学院）；Department of Computer Science & Engineering, Indraprastha Institute of Information Technology, Delhi, New Delhi, 110020, India（印度德里印度信息技术研究所计算机科学与工程系）
RGMem: Renormalization Group-inspired Memory Evolution for Language Agents
School of Computer Science；Engineering, Beihang University, Beijing, China；School of Reliability；Systems Engineering, Beihang University, Beijing, China；State Key Laboratory of Complex \& Critical Software Environment；National Key Laboratory of Reliability；State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences
SouLLMate: An Application Enhancing Diverse Mental Health Support with Adaptive LLMs, Prompt Engineering, and RAG Techniques
Texas A&M University - Corpus Christi（德克萨斯A&M大学-科珀斯克里斯蒂分校）；University of Missouri（密苏里大学）；Delft University of Technology（代尔夫特理工大学）；University of Texas Rio Grande Valley（德克萨斯大学里奥格兰德谷分校）
HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues
College of Design and Innovation, Tongji University（同济大学设计创意学院）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（同济大学上海自主智能无人系统科学中心）
MovieTeller: Tool-augmented Movie Synopsis with ID Consistent Progressive Abstraction
Central Universities（中央高校）；National Natural Science Foundation of China（中国国家自然科学基金委员会）；Research Fund for International Scientists of National Natural Science Foundation of China（中国国家自然科学基金委员会国际科学家研究基金）
SPL: A Socratic Playground for Learning Powered by Large Language Model
Institute for Intelligent Systems, University of Memphis（孟菲斯大学智能系统研究所）；University of Memphis（孟菲斯大学）；School of Computer Science, Carnegie Mellon University（卡内基梅隆大学计算机科学学院）；School of Psychology, Shaanxi Normal University（陕西师范大学心理学院）；School of Psychology, Central China Normal University（华中师范大学心理学院）；Department of Applied Social Sciences, Hong Kong Polytechnic University（香港理工大学应用社会科学系）
Columbia University（哥伦比亚大学）；Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（Inria巴黎- Rocquencourt研究所）；Rajiv Gandhi University（拉贾·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒姆研究实验室）
We present HARE, a new task where reader feedback is used to optimize document summaries for personal interest during the normal flow of reading. This task is related to interactive summarization, where personalized summaries are produced following a long feedback stage where users may read the same sentences many times. However, this process severely interrupts the flow of reading, making it impractical for leisurely reading. We propose to gather minimally-invasive feedback during the reading process to adapt to user interests and augment the document in real-time. Building off of recent adva…
Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document. We propose new metrics of relevance and redundancy using pointwise mutual information (PMI) between sentences, which can be easily computed by a pre-trained language model. Intuitively, a relevant sentence allows readers to infer the document content (high PMI with the document), and a redundant sentence can be inferred from the summary (high PMI with the summary). We then develop a greedy sentence selection algorithm to max…
National University of Singapore（新加坡国立大学）；University of Southern California（南加州大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Kriston AI（Kriston人工智能公司）
Output length is critical to dialogue summarization systems. The dialogue summary length is determined by multiple factors, including dialogue complexity, summary objective, and personal preferences. In this work, we approach dialogue summary length from three perspectives. First, we analyze the length differences between existing models' outputs and the corresponding human references and find that summarization models tend to produce more verbose summaries due to their pretraining objectives. Second, we identify salient features for summary length prediction by comparing different model setti…
In order to build dialogue systems to tackle the ambitious task of holding social conversations, we argue that we need a data driven approach that includes insight into human conversational chit chat, and which incorporates different natural language processing modules. Our strategy is to analyze and index large corpora of social media data, including Twitter conversations, online debates, dialogues between friends, and blog posts, and then to couple this data retrieval with modules that perform tasks such as sentiment and style analysis, topic modeling, and summarization. We aim for personal …
