Summary of Domain-specific Improvement on Psychotherapy Chatbot Using Assistant, by Cheng Kang and Daniel Novak and Katerina Urbanova and Yuqing Cheng and Yong Hu
Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant
by Cheng Kang, Daniel Novak, Katerina Urbanova, Yuqing Cheng, Yong Hu
First submitted to arxiv on: 24 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
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 an innovative approach to improve the performance of large language models (LLMs) in psychotherapy tasks by leveraging domain-specific assistant instructions. The authors introduce a novel adaption fine-tuning method and retrieval augmented generation method to fine-tune pre-trained LLMs on Psychotherapy Assistant Instructions. Experimental results demonstrate that pre-trained LLMs outperform state-of-the-art baselines, showcasing the potential of this approach in psychotherapeutic applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research explores how to make large language models better at helping with therapy tasks by giving them specific instructions and training them on related data. The authors developed a new way to adapt these pre-trained models to work better with therapy assistant instructions. |
Keywords
» Artificial intelligence » Fine tuning » Retrieval augmented generation
