Learning from Mistakes via Cooperative Study Assistant for Large Language Models

6Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

Abstract

Large language models (LLMs) have demonstrated their potential to refine their generation based on their own feedback. However, the feedback from LLM itself is often inaccurate, thereby limiting its benefits. In this paper, we propose Study Assistant for Large LAnguage Model (SALAM), a novel framework with an auxiliary agent to assist the main LLM in learning from mistakes through interactive cooperation. In the gathering phase, the student assistant agent probes the main LLM, analyzes its errors, and collects the interaction in a mistake memory. During the examination phase, the study assistant provides guidelines by retrieving relevant cases to help the main LLM anticipate and avoid similar errors. We first investigate the effectiveness of a general study assistant and then customize it to provide LLM-specific guidance through imitation learning from successful guidance experiences. Our experiments on three LLMs using two challenging frameworks demonstrate that SALAM can significantly boost LLMs by an accuracy margin of up to 6.6 on BBH and 12.6 on BBQ.

Cite

CITATION STYLE

APA

Wang, D., & Li, L. (2023). Learning from Mistakes via Cooperative Study Assistant for Large Language Models. In EMNLP 2023 - 2023 Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 10667–10685). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2023.emnlp-main.659

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free