Auto-Evolve: Enhancing Large Language Model’s Performance via Self-Reasoning Framework

Krishna Aswani, Huilin Lu, Pranav Patankar, Priya Dhalwani, Xue Tan, Jayant Ganeshmohan, Simon Lacasse


Abstract
Recent advancements in prompt engineering strategies, such as Chain-of-Thought (CoT) and Self-Discover, have demonstrated significant potential in improving the reasoning abilities of Large Language Models (LLMs). However, these state-of-the-art (SOTA) prompting strategies rely on a fixed set of static seed reasoning modules like “think step by step” or “break down this problem” intended to simulate human approach to problem-solving. This constraint limits the flexibility of models in tackling diverse problems effectively. In this paper, we introduce Auto-Evolve, a novel framework that enables LLMs to self-create dynamic reasoning modules and downstream action plan, resulting in significant improvements over current SOTA methods. We evaluate Auto-Evolve on the challenging BigBench-Hard (BBH) dataset with Claude 2.0, Claude 3 Sonnet, Mistral Large, and GPT-4, where it consistently outperforms the SOTA prompt strategies. Auto-Evolve outperforms CoT by up to 10.4% and on an average by 7% across these four models. Our framework introduces two innovations: a) Auto-Evolve dynamically generates reasoning modules for each task while aligning with human reasoning paradigm, thus eliminating the need for predefined templates. b) An iterative refinement component, that incrementally refines instruction guidance for LLMs and helps boost performance by average 2.8% compared to doing it in a single step.
Anthology ID:
2024.findings-emnlp.774
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13243–13257
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.774
DOI:
Bibkey:
Cite (ACL):
Krishna Aswani, Huilin Lu, Pranav Patankar, Priya Dhalwani, Xue Tan, Jayant Ganeshmohan, and Simon Lacasse. 2024. Auto-Evolve: Enhancing Large Language Model’s Performance via Self-Reasoning Framework. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13243–13257, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Auto-Evolve: Enhancing Large Language Model’s Performance via Self-Reasoning Framework (Aswani et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.774.pdf