Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents

2023/10/13 by Hyungjoo Chae, Yongho Song, Chae, Hyungjoo +15 · 7 citations
Computer Science · #Topic Modeling #Natural Language Processing Techniques #Speech and dialogue systems

paper · pdf · doi:10.48550/arxiv.2310.09343

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.

Cited by

• Adaptive Multi-Agent Response Refinement in Conversational Systems
• Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning
• SI-Bench: Benchmarking Social Intelligence of Large Language Models in Human-to-Human Conversations
• Revisiting the UID Hypothesis in LLM Reasoning Traces
• Revisiting the Uniform Information Density Hypothesis in LLM Reasoning Traces
• CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
• Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation

Related

• Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules
• Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models
• Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
• Reason first, then respond: Modular Generation for Knowledge-infused Dialogue
• ConceptNet infused DialoGPT for Underlying Commonsense Understanding and Reasoning in Dialogue Response Generation