Large Language Models are In-context Teachers for Knowledge Reasoning

Jiachen Zhao, Zonghai Yao, Zhichao Yang, Hong Yu


Abstract
In this work, we study in-context teaching(ICT), where a teacher provides in-context example rationales to teach a student to reasonover unseen cases. Human teachers are usually required to craft in-context demonstrations, which are costly and have high variance. We ask whether a large language model (LLM) can serve as a more effective in-context teacher for itself or otherLLMs, compared to humans. Inspired by the Encoding Specificity Hypothesis from human episodic memory, we hypothesize thatin-context exemplars crafted by the teacher should match the training data of the student. This hypothesis motivates us to propose Self-Explain where an LLM’s self-elicited explanations are used as in-context demonstrations for prompting it as they are generalized fromthe model’s training examples. Self-Explain is shown to significantly outperform using human-crafted exemplars and other baselines.Furthermore, we reveal that for ICT, rationales from different teacher LLMs or human experts that more resemble the student LLM’s self-explanations are better in-context demonstrations. This supports our encoding specificity hypothesis. We then propose Teach-Back that aligns a teacher LLM with the student to enhance the ICT 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.
Anthology ID:
2024.findings-emnlp.961
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:
16470–16486
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.961/
DOI:
10.18653/v1/2024.findings-emnlp.961
Bibkey:
Cite (ACL):
Jiachen Zhao, Zonghai Yao, Zhichao Yang, and Hong Yu. 2024. Large Language Models are In-context Teachers for Knowledge Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16470–16486, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Large Language Models are In-context Teachers for Knowledge Reasoning (Zhao et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.961.pdf