Pith. sign in

REVIEW 1 cited by

Efficient Knowledge Distillation: Empowering Small Language Models with Teacher Model Insights

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.12586 v1 pith:5ITBDYU2 submitted 2024-09-19 cs.CL

classification cs.CL
keywords modelmodelstokensknowledgelanguagesmallteacherdistillation
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Enhancing small language models for real-life application deployment is a significant challenge facing the research community. Due to the difficulties and costs of using large language models, researchers are seeking ways to effectively deploy task-specific small models. In this work, we introduce a simple yet effective knowledge distillation method to improve the performance of small language models. Our approach utilizes a teacher model with approximately 3 billion parameters to identify the most influential tokens in its decision-making process. These tokens are extracted from the input based on their attribution scores relative to the output, using methods like saliency maps. These important tokens are then provided as rationales to a student model, aiming to distill the knowledge of the teacher model. This method has proven to be effective, as demonstrated by testing it on four diverse datasets, where it shows improvement over both standard fine-tuning methods and state-of-the-art knowledge distillation models. Furthermore, we explore explanations of the success of the model by analyzing the important tokens extracted from the teacher model. Our findings reveal that in 68\% of cases, specifically in datasets where labels are part of the answer, such as multiple-choice questions, the extracted tokens are part of the ground truth.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability

    cs.CL 2025-04 conditional novelty 5.0 of 10

    A small language model distilled with a combination of multitask and counterfactual training on critique-revised explanations produced human-rated higher-quality explanations, while multitask training alone gave the b...

Pith tools