{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/distillm-2-a-contrastive-approach-boosts-the","title":"DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs","arxiv_id":"2503.07067","date":"2025-03-10","proceeding":null,"authors":["Jongwoo Ko","Tianyi Chen","Sungnyun Kim","Tianyu Ding","Luming Liang","Ilya Zharkov","Se-Young Yun"],"abstract":"Despite the success of distillation in large language models (LLMs), most prior work applies identical loss functions to both teacher- and student-generated data. These strategies overlook the synergy between loss formulations and data types, leading to a suboptimal performance boost in student models. To address this, we propose DistiLLM-2, a contrastive approach that simultaneously increases the likelihood of teacher responses and decreases that of student responses by harnessing this synergy. Our extensive experiments show that DistiLLM-2 not only builds high-performing student models across a wide range of tasks, including instruction-following and code generation, but also supports diverse applications, such as preference alignment and vision-language extensions. These findings highlight the potential of a contrastive approach to enhance the efficacy of LLM distillation by effectively aligning teacher and student models across varied data types.","url_abs":"https://arxiv.org/abs/2503.07067v1","url_pdf":"https://arxiv.org/pdf/2503.07067v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"distillm-2-a-contrastive-approach-boosts-the","repo_url":"https://github.com/jongwooko/distillm-2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.07067","atlas_url":"https://app.syntology.ai/?focus=2503.07067","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}