Enhancing knowledge distillation in large language models via domain adaptation

Domain-Adaptive Pre-Training (DAPT) is widely used to improve Large Language Models on specialized domains, yet its interaction with knowledge distillation (KD) remains poorly understood. In particular, intermediate DAPT checkpoints are rarely analyzed, and the evolution of teacher uncertainty across such checkpoints has not been systematically studied. This thesis develops a unified framework to examine how DAPT reshapes teacher confidence and how these shifts influence KD performance, downstream performance and calibration. Using LLaMA-2-7B teachers adapted for 2,000, 5,000, 7,500, and 10,000 DAPT steps, together with Sheared-LLaMA-1.3B students distilled under four KD variants, we evaluate two biomedical QA benchmarks: PubMedQA and BioASQ. We analyze teacher entropy, entropy–performance correlations, and student Expected Calibration Error (ECE) across checkpoints. Our findings reveal three key insights: (1) teacher entropy shifts moderately with deeper DAPT but redistributes most strongly over semantically informative tokens; (2) moderate entropy reduction yields the strongest KD gains for abstractive reasoning tasks such as PubMedQA, whereas extractive QA tasks benefit more from heavily domain-adapted teachers whose predictions are sharper and more concentrated, and (3) student calibration closely tracks teacher entropy, with sharper teachers generally producing better-calibrated models, though excessively low entropy can introduce calibration trade-offs.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Bioinformatics

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Zhang, Xitong (Jacqueline)

Contributors dc:contributor

• He, Jingrui
• Ma, Jiaqi

• Knowledge Distillation
• Large Language Models
• Deep Learning
• Machine Learning
• Artificial Intelligence

Statement dc:rights

• Copyright 2025 Xitong (Jacqueline) Zhang

Language dc:language

en

Handle dc:identifier

https://hdl.handle.net/2142/132689

OAI identifier oai:identifier

oai:www.ideals.illinois.edu:2142/132689