{"slug": "knowledge-distillation-of-black-box-large-language-models", "title": "Knowledge Distillation of Black-Box Large Language Models", "summary": "Researchers introduced Proxy-KD, a method for distilling knowledge from black-box large language models (LLMs) like GPT-4 into smaller models without accessing internal states. Proxy-KD uses a proxy model to facilitate knowledge transfer, outperforming traditional white-box KD techniques. This approach offers a new way to leverage proprietary LLMs for improving smaller models.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 13 Jan 2024 (\n\n[v1](https://arxiv.org/abs/2401.07013v1)), last revised 9 Nov 2024 (this version, v2)]# Title:Knowledge Distillation of Black-Box Large Language Models\n\n[View PDF](/pdf/2401.07013)\n\n[HTML (experimental)](https://arxiv.org/html/2401.07013v2)\n\nAbstract: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.\n\n## Submission history\n\nFrom: Hongzhan Chen [[view email](/show-email/794667b0/2401.07013)]\n\n**Sat, 13 Jan 2024 08:43:32 UTC (359 KB)**\n\n[[v1]](/abs/2401.07013v1)**[v2]** Sat, 9 Nov 2024 01:35:32 UTC (8,288 KB)\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/knowledge-distillation-of-black-box-large-language-models", "canonical_source": "https://arxiv.org/abs/2401.07013", "published_at": "2026-06-28 22:32:04+00:00", "updated_at": "2026-06-28 22:58:04.532741+00:00", "lang": "en", "topics": ["large-language-models", "machine-learning", "artificial-intelligence", "ai-research"], "entities": ["GPT-4", "Proxy-KD"], "alternates": {"html": "https://wpnews.pro/news/knowledge-distillation-of-black-box-large-language-models", "markdown": "https://wpnews.pro/news/knowledge-distillation-of-black-box-large-language-models.md", "text": "https://wpnews.pro/news/knowledge-distillation-of-black-box-large-language-models.txt", "jsonld": "https://wpnews.pro/news/knowledge-distillation-of-black-box-large-language-models.jsonld"}}