Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
This work addresses the challenge of building more coherent and informative chatbots for users by enhancing their ability to reason over implicit information in conversations, representing an incremental improvement in dialogue systems.
The paper tackles the problem of enabling multi-hop commonsense reasoning in conversational agents by proposing a knowledge distillation framework that uses large language models as unreliable teachers and selectively distills consistent rationales, resulting in a model called DOCTOR that significantly improves response quality.
Human-like chatbots necessitate the use of commonsense reasoning in order to effectively comprehend and respond to implicit information present within conversations. Achieving such coherence and informativeness in responses, however, is a non-trivial task. Even for large language models (LLMs), the task of identifying and aggregating key evidence within a single hop presents a substantial challenge. This complexity arises because such evidence is scattered across multiple turns in a conversation, thus necessitating integration over multiple hops. Hence, our focus is to facilitate such multi-hop reasoning over a dialogue context, namely dialogue chain-of-thought (CoT) reasoning. To this end, we propose a knowledge distillation framework that leverages LLMs as unreliable teachers and selectively distills consistent and helpful rationales via alignment filters. We further present DOCTOR, a DialOgue Chain-of-ThOught Reasoner that provides reliable CoT rationales for response generation. We conduct extensive experiments to show that enhancing dialogue agents with high-quality rationales from DOCTOR significantly improves the quality of their responses.