Summary of Cocoa: Cbt-based Conversational Counseling Agent Using Memory Specialized in Cognitive Distortions and Dynamic Prompt, by Suyeon Lee et al.
COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt
by Suyeon Lee, Jieun Kang, Harim Kim, Kyoung-Mee Chung, Dongha Lee, Jinyoung Yeo
First submitted to arxiv on: 27 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper develops CoCoA, a conversational agent that provides mental health care by applying Cognitive Behavioral Therapy (CBT) techniques. The agent identifies and addresses cognitive distortions in client statements, utilizing a memory system to efficiently manage information. To ensure appropriate responses, the model introduces dynamic prompting to flexibly apply CBT techniques. Evaluations were conducted using a dataset created through dialogues with characters from Character.ai, showing a statistically significant difference compared to other models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary CoCoA is a new kind of chatbot that helps people with mental health problems. It uses ideas from a type of therapy called Cognitive Behavioral Therapy (CBT) to understand what someone is saying and respond in a helpful way. The chatbot remembers important information and can adjust its responses based on the conversation. The paper tested CoCoA by having it talk to characters created for a website, and it did much better than other models. |
Keywords
» Artificial intelligence » Prompting
