SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.09343 · EMNLP · 2023

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

Youngjae Yu, Dongyeop Kang, Hyungjoo Chae, Dongha Lee, Jinyoung Yeo, Minjin Kim, Taeyoon Kwon, Yongho Song, Kai Tzu, -Iunn Ong

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
hwchase17/langchain canonical 1 of 1
silin159/comfact canonical 0 of 1
FunctionStatusWhere it lives
import_attr Ran hwchase17/langchain/libs/core/langchain_core/_import_utils.py
code served (permissive licence) · get_code("30cbe01b2f78e405")
run_batch_linking Not yet run silin159/comfact/baseline/utils/model.py
code served (permissive licence) · get_code("165942aa74493286")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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 1 . We conduct extensive experiments to show that enhancing dialogue agents with high-quality rationales from DOCTOR significantly improves the quality of their responses 2 . * Equal contribution 1 We release our source code on https://github.com/ kyle8581/DialogueCoT. 2 We release demonstrations of dialogue CoT reasoning in https://dialoguecot.web.app/.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.09343")
get_code_for_paper("2310.09343")
have("2310.09343")

Connect an agent — have() is free.