CogChain: Enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning

We will release ESChain as soon as possible. 💪

Star this repo to receive the latest notifications. 🙌

We propose CogChain, a cognitive chain-of-thought (CoT) reasoning framework that mimics a human supporter’s cognitive process for emotional support conversation. Specifically, CogChain employs a chained structure to analyze the seeker’s issues, infer internal thoughts, determine behavioral intentions, and select appropriate strategies to achieve support goals.

CogChain Framework

Pipeline of our methodology

Statistics of ESChain dataset

Human Evaluation

Ablation study on different elements of CogChian

Case study

Citation

If you find our work useful, please cite our paper.

@inproceedings{DBLP:conf/nlpcc/CaoCBFCWHY24,

author = {Yaru Cao and Zhuang Chen and Guanqun Bi and Yulin Feng and Min Chen and Fucheng Wan and Minlie Huang and Hongzhi Yu},

editor = {Derek F. Wong and Zhongyu Wei and Muyun Yang},

title = {Enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning},

booktitle = {Natural Language Processing and Chinese Computing - 13th National {CCF} Conference, {NLPCC} 2024, Hangzhou, China, November 1-3, 2024, Proceedings, Part {I}},

series = {Lecture Notes in Computer Science},

volume = {15359},

pages = {175--187},

publisher = {Springer},

year = {2024},

url = {https://doi.org/10.1007/978-981-97-9431-7\_14},

doi = {10.1007/978-981-97-9431-7_14},

timestamp = {Mon, 18 Nov 2024 15:16:29 +0100},

biburl = {https://dblp.org/rec/conf/nlpcc/CaoCBFCWHY24.bib},

bibsource = {dblp computer science bibliography, https://dblp.org} }