Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model
This addresses the problem of improving social bonding and interaction quality in conversational AI for users, though it appears incremental as it builds on existing LLM methods with new data and training.
The authors tackled the challenge of enabling LLM-based conversational agents to plan appropriate conversational skills like humans, by creating a skill-of-mind-annotated dataset of roughly 100K conversations and training models (Thanos) that significantly enhance response quality and promote prosocial behavior in human evaluations.
To increase social bonding with interlocutors, humans naturally acquire the ability to respond appropriately in a given situation by considering which conversational skill is most suitable for the response - a process we call skill-of-mind. For large language model (LLM)-based conversational agents, planning appropriate conversational skills, as humans do, is challenging due to the complexity of social dialogue, especially in interactive scenarios. To address this, we propose a skill-of-mind-annotated conversation dataset, named Multifaceted Skill-of-Mind, which includes multi-turn and multifaceted conversational skills across various interactive scenarios (e.g., long-term, counseling, task-oriented), grounded in diverse social contexts (e.g., demographics, persona, rules of thumb). This dataset consists of roughly 100K conversations. Using this dataset, we introduce a new family of skill-of-mind-infused LLMs, named Thanos, with model sizes of 1B, 3B, and 8B parameters. With extensive experiments, these models successfully demonstrate the skill-of-mind process and exhibit strong generalizability in inferring multifaceted skills across a variety of domains. Moreover, we show that Thanos significantly enhances the quality of responses generated by LLM-based conversational agents and promotes prosocial behavior in human evaluations.