# 黑盒大语言模型的知识蒸馏

- 来源：Hacker News 热门（buzzing.cc 中文翻译）
- 作者：babelfish
- 发布时间：2026-06-29 18:19
- AIHOT 分数：39
- AIHOT 链接：https://aihot.virxact.com/items/cmqz2zp7m0038sldy5bnj6s1u
- 原文链接：https://arxiv.org/abs/2401.07013

## AI 摘要

GPT-4 等闭源大语言模型性能优异，但因其作为黑盒教师无法提供内部状态，限制了知识蒸馏的效果。Proxy-KD 方法引入一个代理模型，实现从黑盒 LLM 到小模型的高效知识迁移。实验结果显示，Proxy-KD 不仅提升了黑盒教师蒸馏的性能，还超越了传统白盒蒸馏技术。

## 正文

Computer Science > Computation and Language

[Submitted on 13 Jan 2024 (v1), last revised 9 Nov 2024 (this version, v2)]

Title:Knowledge Distillation of Black-Box Large Language Models

Authors:Hongzhan Chen, Ruijun Chen, Yuqi Yi, Xiaojun Quan, Chenliang Li, Ming Yan, Ji Zhang

View PDF HTML (experimental)

Abstract:Given the exceptional performance of proprietary large language models (LLMs) like GPT-4, recent research has increasingly focused on boosting the capabilities of smaller models through knowledge distillation (KD) from these powerful yet black-box teachers. While leveraging the high-quality outputs of these teachers is advantageous, the inaccessibility of their internal states often limits effective knowledge transfer. To overcome this limitation, we introduce Proxy-KD, a novel method that uses a proxy model to facilitate the efficient transfer of knowledge from black-box LLMs to smaller models. Our experiments show that Proxy-KD not only enhances the performance of KD from black-box teacher models but also surpasses traditional white-box KD techniques.~This approach presents a compelling new avenue for distilling knowledge from advanced LLMs.

Subjects: Computation and Language (cs.CL)

Cite as: arXiv:2401.07013 [cs.CL]

(or arXiv:2401.07013v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2401.07013

arXiv-issued DOI via DataCite

Submission history

From: Hongzhan Chen [view email]
[v1] Sat, 13 Jan 2024 08:43:32 UTC (359 KB)
[v2] Sat, 9 Nov 2024 01:35:32 UTC (8,288 KB)

Full-text links:

Access Paper:

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

< prev | next >

new | recent | 2024-01

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Bookmark

Bibliographic and Citation Tools

Bibliographic Explorer (What is the Explorer?)

Connected Papers (What is Connected Papers?)

Litmaps (What is Litmaps?)

scite Smart Citations (What are Smart Citations?)

Code, Data and Media Associated with this Article

alphaXiv (What is alphaXiv?)

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub (What is DagsHub?)

Gotit.pub (What is GotitPub?)

Hugging Face (What is Huggingface?)

ScienceCast (What is ScienceCast?)

Demos

Replicate (What is Replicate?)

Hugging Face Spaces (What is Spaces?)

TXYZ.AI (What is TXYZ.AI?)

Recommenders and Search Tools

Influence Flower (What are Influence Flowers?)

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)