Self-Discover: Large Language Models Self-Compose Reasoning Structures
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913223811268608 |
|---|---|
| author | Zhou, Pei Pujara, Jay Ren, Xiang Chen, Xinyun Cheng, Heng-Tze Le, Quoc V. Chi, Ed H. Zhou, Denny Mishra, Swaroop Zheng, Huaixiu Steven |
| author_facet | Zhou, Pei Pujara, Jay Ren, Xiang Chen, Xinyun Cheng, Heng-Tze Le, Quoc V. Chi, Ed H. Zhou, Denny Mishra, Swaroop Zheng, Huaixiu Steven |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03620 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | 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 Artificial Intelligence Computation and Language 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. |
| title | Self-Discover: Large Language Models Self-Compose Reasoning Structures |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2402.03620 |