Self-Discover: Large Language Models Self-Compose Reasoning Structures
Zhou, Pei, Pujara, Jay, Ren, Xiang, Chen, Xinyun, Cheng, Heng-Tze, Le, Quoc V., Chi, Ed H., Zhou, Denny, Mishra, Swaroop, Zheng, Huaixiu Steven
–arXiv.org Artificial Intelligence
We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a self-discovery process where LLMs select multiple atomic reasoning modules such as critical thinking and step-by-step thinking, and compose them into an explicit reasoning structure for LLMs to follow during decoding. SELF-DISCOVER substantially improves GPT-4 and PaLM 2's performance on challenging reasoning benchmarks such as BigBench-Hard, grounded agent reasoning, and MATH, by as much as 32% compared to Chain of Thought (CoT). Furthermore, SELF-DISCOVER outperforms inference-intensive methods such as CoT-Self-Consistency by more than 20%, while requiring 10-40x fewer inference compute. Finally, we show that the self-discovered reasoning structures are universally applicable across model families: from PaLM 2-L to GPT-4, and from GPT-4 to Llama2, and share commonalities with human reasoning patterns.
arXiv.org Artificial Intelligence
Feb-5-2024
- Country:
- North America
- Canada (0.14)
- United States > California (0.14)
- North America
- Genre:
- Research Report (1.00)
- Technology: