Summary of Cognition Chain For Explainable Psychological Stress Detection on Social Media, by Xin Wang et al.
Cognition Chain for Explainable Psychological Stress Detection on Social Media
by Xin Wang, Boyan Gao, Yi Dai, Lei Cao, Liang Zhao, Yibo Yang, David Clifton
First submitted to arxiv on: 18 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Human-Computer Interaction (cs.HC)
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 The abstract proposes a new approach to detecting stress using Large Language Models (LLMs), which are capable of generating explanations for their predictions through the use of generative properties. However, existing LLMs lack guidance from psychological cognitive theory, leading to limited explainability and trust. The authors introduce Cognition Chain, a method that explicates the generation of stress through a step-by-step cognitive perspective based on cognitive appraisal theory. This approach is used to develop an instruction-tuning dataset for LLMs called CogInstruct, which enables autonomous generation and refinement of instructional data. The resulting model, CogLLM, achieves outstanding performance while enhancing explainability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Stress affects many people worldwide, leading to serious mental health problems. Detecting stress early can prevent these disorders. Current models are not very good at explaining their decisions, making it hard to use them in real-world situations. Large Language Models (LLMs) are special because they can generate explanations for their predictions. But most LLMs are trained without considering how our brains work. To improve this, the authors developed a new approach called Cognition Chain. It’s like a step-by-step guide that shows how stress develops in our minds. They used this approach to create a special dataset that helps LLMs learn to detect stress better and explain their decisions. |
Keywords
» Artificial intelligence » Instruction tuning
