TPD: Enhancing Student Language Model Reasoning via Principle Discovery and Guidance
Research Area: Inference algorithms for LMs, LMs and interactions
Keywords: Principle discovery,Teacher-student framework,Reasoning
TL;DR: We introduce a teacher-student framework TPD that enhances the effectiveness of teacher models in educating student models.
Abstract: Large Language Models (LLMs) have recently showcased remarkable reasoning abilities. However, larger models often surpass their smaller counterparts in reasoning tasks, posing the challenge of effectively transferring these capabilities from larger models. Existing approaches heavily rely on extensive fine-tuning data or continuous interactions with a superior teacher LLM during inference. We introduce a principle-based teacher-student framework called Teaching via Principle Discovery (TPD) to address these limitations. Inspired by human learning mechanisms, TPD mimics the interaction between a teacher and a student using a principle-based approach. The teacher LLM generates problem-solving instructions and corrective principles based on the student LLM's errors. These principles guide the refinement of instructions and the selection of instructive examples from a validation set. This enables the student model to learn from both the teacher's guidance and its own mistakes. Once the student model begins making inferences, TPD requires no further intervention from the teacher LLM. Through extensive experiments across eight reasoning tasks, we demonstrate the effectiveness of TPD. Compared to standard chain-of-thought prompting, TPD significantly improves the student model's performance, achieving an average improvement of 6.2\%.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 1463
Loading