Hedges allow speakers to mark utterances as provisional, whether to signal non-prototypicality or "fuzziness", to indicate a lack of commitment to an utterance, to attribute responsibility for a statement to someone else, to invite input from a partner, or to soften critical feedback in the service of face-management needs. Here we focus on hedges in an experimentally parameterized corpus of 63 Roadrunner cartoon narratives spontaneously produced from memory by 21 speakers for co-present addressees, transcribed to text (Galati and Brennan, 2010). We created a gold standard of hedges annotated by human coders (the Roadrunner-Hedge corpus) and compared three LLM-based approaches for hedge detection: fine-tuning BERT, and zero and few-shot prompting with GPT-4o and LLaMA-3. The best-performing approach was a fine-tuned BERT model, followed by few-shot GPT-4o. After an error analysis on the top performing approaches, we used an LLM-in-the-Loop approach to improve the gold standard coding, as well as to highlight cases in which hedges are ambiguous in linguistically interesting ways that will guide future research. This is the first step in our research program to train LLMs to interpret and generate collateral signals appropriately and meaningfully in conversation.
Mary, the Cheeseburger-Eating Vegetarian: Do LLMs Recognize Incoherence in Narratives?
Department of Computer Science and Engineering, University of Minnesota（计算机科学与工程系，明尼苏达大学）；Department of Educational Psychology, University of Minnesota（教育心理学系，明尼苏达大学）；Department of Linguistics, Hamline University（语言学系，哈姆林大学）；Department of English, University of Minnesota（英语系，明尼苏达大学）
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of the Basque Country UPV/EHU（巴斯克地区大学）
The growing interest in employing counter narratives for hatred intervention brings with it a focus on dataset creation and automation strategies. In this scenario, learning to recognize counter narrative types from natural text is expected to be useful for applications such as hate speech countering, where operators from non-governmental organizations are supposed to answer to hate with several and diverse arguments that can be mined from online sources. This paper presents the first multilingual work on counter narrative type classification, evaluating SoTA pre-trained language models in mon…
Shanghai Jiao Tong University（上海交通大学）；China Merchants Bank Credit Card Center（招商银行信用卡中心）
Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models. These features either require additional knowledge to recognize or make the resulting models harder to tune. To bridge the format gap between dialogues and narrative summaries in dialogue summarization tasks, we propose to post-train pretrained language models (PLMs) to rephrase from dialogue to narratives. After that, the model is fine-tuned for dialogue summarization as usual. Comprehensive experiments show that our approach signific…
Information Sciences Institute, University of Southern California（南加州大学信息科学研究所）；Department of Computer Science, University of Southern California（南加州大学计算机科学系）；Department of Computer Science, Vrije Universiteit Amsterdam（阿姆斯特丹自由大学计算机科学系）；Computational Linguistics & Text Mining Lab, Vrije Universiteit Amsterdam（阿姆斯特丹自由大学计算语言学与文本挖掘实验室）
AR$^2$: Adversarial Reinforcement Learning for Abstract Reasoning in Large Language Models
Department of Mathematical Sciences National Chengchi University Taipei Taiwan（数学科学系 国立政治大学 台北 台湾）；Department of Computer Science National Chengchi University Taipei Taiwan（计算机科学系 国立政治大学 台北 台湾）；Institute of Information Science Academia Sinica Taipei Taiwan（信息科学研究所 中国学术院 台北 台湾）；National Chengchi University（国立政治大学）
AdaPPA: Adaptive Position Pre-Fill Jailbreak Attack Approach Targeting LLMs
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
From Repetition to Recognition: Inductive Discovery of Disinformation Narratives
Technische Universität Berlin（柏林工业大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；Johannes Gutenberg-Universität Mainz（美因茨约翰内斯·古腾堡大学）；Centre for European Research in Trusted AI (CERTAIN)（欧洲可信人工智能研究中心）
Through the Prism of Culture: Evaluating LLMs' Understanding of Indian Subcultures and Traditions
Amar Nath and Shashi Khosla School of Information Technology, Indian Institute of Technology Delhi（阿玛纳特和沙希·科斯拉信息科技学院，印度理工学院德里）；Computer Science and Engineering Department, Delhi Technological University（德里技术大学计算机科学与工程系）；Department of Computer Science and Engineering, Indian Institute of Technology Kharagpur（印度理工学院Khargpur计算机科学与工程系）
An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
Department of Archeology and Museology, Shanghai University（考古与博物馆学系，上海大学）；National Collaborative Research Center for Revolutionary Cultural Heritage at Memorial of the First CPC National Congress & Shanghai University（革命文化遗产国家联合研究中心，中共一大会址纪念馆与上海大学）；School of Management, Shanghai University（管理学院，上海大学）；Nanyang Technological University（南洋理工大学）
