LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement
Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, Shuicheng Yan
Abstract
This paper introduces the innovative “LLMs-as-Instructors” framework, which leverages the advanced Large Language Models (LLMs) to autonomously enhance the training of smaller target models. Inspired by the theory of “Learning from Errors”, this framework employs an instructor LLM to meticulously analyze the specific errors within a target model, facilitating targeted and efficient training cycles. Within this framework, we implement two strategies: “Learning from Error,” which focuses solely on incorrect responses to tailor training data, and “Learning from Error by Contrast,” which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors. Our empirical studies, conducted with several open-source models, demonstrate significant improvements across multiple benchmarks, including mathematical reasoning, coding abilities, and factual knowledge. Notably, the refined Llama-3-8b-Instruction has outperformed ChatGPT, illustrating the effectiveness of our approach. By leveraging the strengths of both strategies, we have attained a more balanced performance improvement on both in-domain and out-of-domain benchmarks.- Anthology ID:
- 2024.findings-emnlp.654
- 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:
- 11185–11208
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.654/
- DOI:
- 10.18653/v1/2024.findings-emnlp.654
- Cite (ACL):
- Jiahao Ying, Mingbao Lin, Yixin Cao, Wei Tang, Bo Wang, Qianru Sun, Xuanjing Huang, and Shuicheng Yan. 2024. LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 11185–11208, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement (Ying et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-emnlp.654.pdf