{"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/token-level-adaptation-of-lora-adapters-for","title":"Token-Level Adaptation of LoRA Adapters for Downstream Task Generalization","arxiv_id":"2311.10847","date":"2023-11-17","proceeding":null,"authors":["Joshua Belofsky"],"abstract":"This paper introduces a method for adapting LoRA adapters in smaller-sized language models to arbitrary downstream tasks. Unlike standard mixture-of-expert architectures, our method employs a gradient-free routing function to choose a weighted combination of experts without increasing the compute requirements for training or inference. The results show that token-level adaptation of LoRA adapters outperforms the base Llama-2-7b model across mathematical (GSM8K), scientific (ARC-Challenge), reading comprehension (SQuAD), and coding (CodeAlpaca-20k) tasks. Further evaluations also show that the average performance of token-level adaptation outperforms individual models fine-tuned for each of the tasks with the best performance observed in adaptation of every-other token during inference. The code for this study is made available through a public repository.","url_abs":"https://arxiv.org/abs/2311.10847v2","url_pdf":"https://arxiv.org/pdf/2311.10847v2.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":"token-level-adaptation-of-lora-adapters-for","repo_url":"https://github.com/jb-01/lora-tle","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2311.10847","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}