Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
akhaliq 
posted an update Feb 7
Post
Self-Discover

Large Language Models Self-Compose Reasoning Structures

paper page: Self-Discover: Large Language Models Self-Compose Reasoning Structures (2402.03620)

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.
In this post