Summary of Tpd: Enhancing Student Language Model Reasoning Via Principle Discovery and Guidance, by Haorui Wang (1) et al.
TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance
by Haorui Wang, Rongzhi Zhang, Yinghao Li, Lingkai Kong, Yuchen Zhuang, Xiusi Chen, Chao Zhang
First submitted to arxiv on: 24 Jan 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 In this research paper, scientists tackle the challenge of transferring large language models’ (LLMs) reasoning capabilities to smaller models without relying on extensive fine-tuning data or continuous interactions with a superior teacher LLM during inference. The authors introduce a novel principle-based teacher-student framework called Teaching via Principle Discovery (TPD), which mimics human learning mechanisms by generating problem-solving instructions and corrective principles based on the student LLM’s errors. This allows the student model to learn from both the teacher’s guidance and its own mistakes, achieving significant improvements in performance across eight reasoning tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Large language models can reason well, but transferring their abilities to smaller models is tricky. Scientists have a solution: a new approach called Teaching via Principle Discovery (TPD). It works like how humans learn – by getting instructions and correcting mistakes. The teacher LLM gives guidance, and the student LLM learns from its own errors too. This way, the student model gets better without needing more help. In fact, it performs 6.2% better on average. |
Keywords
» Artificial intelligence » Fine tuning » Inference » Student model
