Pith. sign in

REVIEW 2 cited by

Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application

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 2407.01885 v1 pith:WWVO2M36 submitted 2024-07-02 cs.CL cs.AI

classification cs.CLcs.AI
keywords distillationmethodsevaluationknowledgelanguagellmsmodelssurvey
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large Language Models (LLMs) have showcased exceptional capabilities in various domains, attracting significant interest from both academia and industry. Despite their impressive performance, the substantial size and computational demands of LLMs pose considerable challenges for practical deployment, particularly in environments with limited resources. The endeavor to compress language models while maintaining their accuracy has become a focal point of research. Among the various methods, knowledge distillation has emerged as an effective technique to enhance inference speed without greatly compromising performance. This paper presents a thorough survey from three aspects: method, evaluation, and application, exploring knowledge distillation techniques tailored specifically for LLMs. Specifically, we divide the methods into white-box KD and black-box KD to better illustrate their differences. Furthermore, we also explored the evaluation tasks and distillation effects between different distillation methods, and proposed directions for future research. Through in-depth understanding of the latest advancements and practical applications, this survey provides valuable resources for researchers, paving the way for sustained progress in this field.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Dynamics of Learning under User Choice: Overspecialization and Peer-Model Probing

    cs.LG 2026-02 conditional novelty 7.0 of 10

    In competitive ML markets, standard gradient training can drive learners into overspecialized equilibria with arbitrarily poor global performance; a proposed 'peer probing' algorithm provably escapes this under inform...

  2. EasyDistill: A Comprehensive Toolkit for Effective Knowledge Distillation of Large Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    EasyDistill packages established LLM knowledge-distillation techniques into a single modular toolkit with released distilled models, datasets, and Alibaba Cloud integration.

Pith tools