Failures Pave the Way: Enhancing Large Language Models through Tuning-free Rule Accumulation

Zeyuan Yang, Peng Li, Yang Liu

Submission Type: Regular Long Paper

Submission Track: Language Modeling and Analysis of Language Models

Keywords: large langauge models, zero-shot learning, prompt

Abstract: Large Language Models (LLMs) have showcased impressive performance. However, due to their inability to capture relationships among samples, these frozen LLMs inevitably keep repeating similar mistakes. In this work, we propose our Tuning-free Rule Accumulation (TRAN) framework, which guides LLMs in improving their performance by learning from previous mistakes. Considering data arrives sequentially, LLMs gradually accumulate rules from incorrect cases, forming a rule collection. These rules are then utilized by the LLMs to avoid making similar mistakes when processing subsequent inputs. Moreover, the rules remain independent of the primary prompts, seamlessly complementing prompt design strategies. Experimentally, we show that TRAN improves over recent baselines by a large margin.

Submission Number: 3882