Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents
Hyungjoo Chae, Yongho Song, Kai Ong, Taeyoon Kwon, Minjin Kim, Youngjae Yu, Dongha Lee, Dongyeop Kang, Jinyoung Yeo
Abstract
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.- Anthology ID:
- 2023.emnlp-main.342
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5606–5632
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.342
- DOI:
- 10.18653/v1/2023.emnlp-main.342
- Cite (ACL):
- Hyungjoo Chae, Yongho Song, Kai Ong, Taeyoon Kwon, Minjin Kim, Youngjae Yu, Dongha Lee, Dongyeop Kang, and Jinyoung Yeo. 2023. Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 5606–5632, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents (Chae et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2023.emnlp-main.342.pdf