Oct 13, 2023 · We propose a knowledge distillation framework that leverages LLMs as unreliable teachers and selectively distills consistent and helpful rationales via ...

Dec 6, 2023 · We posit that commonsense reasoning in a conversation requires multiple hops to capture such implicit details scattered across multiple turns ( ...

Abstract. Human-like chatbots necessitate the use of commonsense reasoning in order to effectively comprehend and respond to implicit information present ...

Official repository of Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents accepted at EMNLP 2023.

Oct 7, 2023 · The paper tries to improve common sense reasoning over multiple turns in conversational agents by augmenting with a conversation rationale ...

Dec 8, 2023 · On-demand video platform giving you access to lectures from conferences worldwide.

Feb 27, 2024 · Recent methods based on chain-of-thought (CoT) style prompting have improved the reasoning abilities of LLMs, showing promising results on tasks ...

Oct 22, 2023 · A dialogue commonsense reasoner that generates Chain-of-Thought knowledge in a multi-hop manner given a dialogue history.

Dialogue Chain-of-Thought Distillation for Commonsense-aware Conversational Agents. Hyungjoo Chae | Yongho Song | Kai Ong | Taeyoon Kwon | Minjin Kim ...

Promoting openness in scientific communication and the peer-review process.