Social influence (SI) is the change in an individual's thoughts, feelings, attitudes, or behaviors from interacting with another individual or a group. For example, a buyer uses SI skills to negotiate trade-offs and build rapport with the seller. SI is ubiquitous in everyday life, and hence, realistic human-machine conversations must reflect these dynamics, making it essential to model and understand SI in dialogue research systematically. This would improve SI systems' ability to understand users’ utterances, tailor communication strategies, personalize responses, and actively lead conversations. These challenges draw on perspectives not only from NLP and AI research but also from Game Theory, Affective Computing, Communication, and Social Psychology.
SI dialogue tasks like negotiation, persuasion, therapy, and argumentation have recently gained traction. Current conversational systems emphasize modeling system strategies using dialogue acts and strategy annotations or modeling users. Prior work also explored related tasks crucial for the eventual development of SI systems, namely outcome prediction, argument mining, and lie detection. However, these efforts are scattered, and only limited efforts focus on building useful systems exhibiting SI skills, such as chatbots. Ensuring AI-driven models’ safety, interpretability, and integration into real-time applications that simulate or analyze SI remains challenging.
We are excited to host the Third Workshop on Social Influence in Conversations (SICon 2025). SICon 2025 will be a one-day hybrid event, co-located with ACL 2025 in Vienna, Austria.
Persuasion for Social Good: How to Build and Break Chatbots
Persuasion is important in numerous situations like healthy habit promotion, and emotional support. As AI gets more involved in our daily life, it becomes critical to study how they can persuade humans and how persuasive they are. In this talk, I will cover (1) how to build such persuasive AI systems that can persuade, negotiate, and cooperate with other humans in the game of Diplomacy. (2) I will also discuss how humans perceive such specialized AI systems. This study validates the necessity of California's Autobot Law and proposes guidance to regulate such systems. (3) As these systems become more powerful, AI safety problems become more important. So I will describe how to persuade AI models to jailbreak them and study AI safety problems. Finally, I will conclude with my long-term vision to further study persuasion from a multi-angle approach that combines Artificial Intelligence, Human-Computer Interaction, and social sciences.
Bio: Weiyan Shi is an assistant professor at Northeastern University. Her research interests are persuasive dialogue systems, and AI safety. She is recognized as MIT Technology Review 35 Innovators under 35, Rising Star in Machine Learning and Rising Star in EECS. She has received a Best Social Impact Paper, an Outstanding Paper, and a Best Paper Nomination for her work on persuasive dialogues at ACL 2019 and ACL 2024. She was also a core team member behind a Science publication on the first negotiation AI agent, Cicero, that achieved a human level in the game of Diplomacy. This work has been featured in The New York Times, The Washington Post, MIT Technology Review, Forbes, and other major media outlets.
Meta-Cultural Competence: What LLMs Should Know About Culture to Be Good Conversationalists
Anthropologist Dan Sperber once remarked that “culture is the precipitate of cognition and communication within a human population.” Culture, in this sense, both shapes and is shaped by the flow of conversation. For conversational AI systems to truly engage users meaningfully, they must be capable of interpreting the user's perspective—something that inherently involves cultural understanding.
Yet culture is notoriously hard to pin down: it resists fixed definitions and defies any quatification. In this talk, I propose a computational framework for meta-cultural competence —one that treats cultural knowledge not as static content but as a dynamic prior. This prior informs conversational interpretation and generation, while being continuously refined through mechanisms of explication (surfacing implicit norms or values) and negotiation (adapting meaning in interaction). The goal is to move toward systems that are not just culturally sensitive, but culturally responsive—capable of evolving alongside the user’s own communicative context.
Bio: Monojit Choudhury is a professor of Natural Language Processing at Mohommed Bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi. Prior to this, he was a principal scientist at Microsoft Research India and Microsoft Turing. Prof Choudhury's research interests lie in the intersection of NLP, Social and Cultural aspects of Technology use, and Ethics. In particular, he has been working on multilingual and multicultural aspects of large language models (LLMs), their use in low resource languages and making LLMs more inclusive and safer. Prof Choudhury takes a keen interest in popularizing linguistics and AI through puzzle solving; he is the general chair of Indian national linguistics Olympiad, the founding co-chair of Asia-Pacific linguistics Olympiad, and a founding board-member of International AI Olympiad. He holds a BTech and PhD degree in Computer Science and Engineering from IIT Kharagpur.
Direct paper submissions
Direct submission deadline: April 15, 2025
Notification of acceptance: May 20, 2025
Camera-ready paper deadline: June 6, 2025
Pre-recorded video due (hard deadline): July 7, 2025
Workshop dates: July 31, 2025
ACL Rolling Review (ARR) submissions
Pre-reviewed (ARR) submission deadline: April 15, 2025
Note: all deadlines are 11:59 PM UTC-12:00 (or AoE, “Anywhere on Earth”).