# Tebmer/Awesome-Knowledge-Distillation-of-LLMs

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

Repository: https://github.com/Tebmer/Awesome-Knowledge-Distillation-of-LLMs
Canonical: https://ross.abutalabs.com/products/awesome-knowledge-distillation-of-llms
License Family: other
Topics: data-augmentation, instruction-following, kd, knowledge-distillation, large-language-model, llm, self-training, survey, compression, data-synthesis, feedback, multi-modal, self-distillation, alignment, supervised-finetuning
Last push: 2025-03-09T15:06:41+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 10, release rhythm 35, longevity 66
- inputs: {"age_days": 937, "days_push": 542, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1305, forks 73 (observed 2026-08-28T04:04:18.603307+00:00)

## What it is
A curated awesome-list of research papers accompanying the survey 'A Survey on Knowledge Distillation of Large Language Models'. It organizes KD literature into knowledge elicitation, distillation algorithms, and skill/vertical distillation of LLMs, updated weekly.

## Use cases
- find papers on distilling GPT-4 capabilities into smaller open-source models
- learn how to compress a large language model via knowledge distillation
- research self-improvement and self-training techniques for LLMs
- find data augmentation methods using LLM-generated data for fine-tuning
- survey multi-modal and alignment distillation approaches
- prepare a literature review on LLM knowledge distillation

## When to choose
- you need a curated, regularly updated reading list on LLM knowledge distillation
- you want the taxonomy from the accompanying survey paper to guide research
- you are exploring teacher-student training, self-distillation, or LLM-based data synthesis

## When to avoid
- you need runnable code or a software library rather than paper references
- you want general machine learning distillation outside the LLM context
- you need a maintained tool with a license and releases

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, llm-training, rag, prompt-engineering, data-science
- domain: large-language-models, machine-learning, artificial-intelligence, awesome-lists, tutorials
- platform: cross-platform
- tags: awesome-list, knowledge-distillation, survey, papers, model-compression, self-training, data-augmentation, alignment, instruction-tuning

## Member repositories
- Tebmer/Awesome-Knowledge-Distillation-of-LLMs (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:18.603307+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:51:00.966818+00:00, confidence not recorded.
  - readme: https://github.com/Tebmer/Awesome-Knowledge-Distillation-of-LLMs (fetched 2026-08-28T04:04:18.603307+00:00, sha e4f72f4c398a)
- Data as of 2026-08-30T08:39:29.467469+00:00.