Paper ID: 2311.06985

Large Language Models are In-context Teachers for Knowledge Reasoning

Jiachen Zhao, Zonghai Yao, Zhichao Yang, Hong Yu

Chain-of-thought (CoT) prompting teaches large language models (LLMs) in context to reason over queries that require more than mere information retrieval. However, human experts are usually required to craft demonstrations for in-context learning (ICL), which is expensive and has high variance. More importantly, how to craft helpful reasoning exemplars for ICL remains unclear. In this work, we investigate whether LLMs can be better in-context teachers for knowledge reasoning. We follow the ``encoding specificity'' hypothesis in human's memory retrieval to assume in-context exemplars at inference should match the encoding context in training data. We are thus motivated to propose Self-Explain to use one LLM's self-elicited explanations as in-context demonstrations for prompting it as they are generalized from the model's training examples. Self-Explain is shown to significantly outperform using human-crafted exemplars and other baselines. We further reveal that for in-context teaching, rationales by distinct teacher LLMs or human experts that more resemble the student LLM's self-explanations are better demonstrations, which supports our encoding specificity hypothesis. We then propose Teach-Back that aligns the teacher LLM with the student to enhance the in-context teaching performance. For example, Teach-Back enables a 7B model to teach the much larger GPT-3.5 in context, surpassing human teachers by around 5% in test accuracy on medical question answering.

Submitted: Nov 12, 2023