Summary of Erd: a Framework For Improving Llm Reasoning For Cognitive Distortion Classification, by Sehee Lim et al.
ERD: A Framework for Improving LLM Reasoning for Cognitive Distortion Classification
by Sehee Lim, Yejin Kim, Chi-Hyun Choi, Jy-yong Sohn, Byung-Hoon Kim
First submitted to arxiv on: 21 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 proposes ERD, a system that utilizes Large Language Models (LLMs) for cognitive distortion classification in psychotherapy. The authors recognize the importance of identifying cognitive distortions from patients’ utterances, especially in cognitive behavioral therapy. ERD improves LLM-based performance by introducing two additional modules: part extraction and multi-agent debate. Experimental results on a public dataset demonstrate improved multi-class F1 scores and binary specificity scores, particularly in debiasing baseline methods with high false positive rates. The proposed method also benefits from providing the summary of multi-agent debate to LLMs. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses computers to help people get better therapy. It’s like having a super smart assistant that can understand what you’re saying and help therapists figure out what’s going on in your mind. The researchers came up with a new way to make these computer systems better by adding some extra steps: finding the important parts of what you said, and then having multiple people discuss why it’s important. This helps the system be more accurate and not get confused as easily. It could make therapy even more helpful for people. |
Keywords
* Artificial intelligence * Classification
