{"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/collaboratively-adding-new-knowledge-to-an","title":"Collaboratively adding new knowledge to an LLM","arxiv_id":"2410.14753","date":"2024-10-18","proceeding":null,"authors":["Rhui Dih Lee","Laura Wynter"],"abstract":"We address the question of how to successively add new knowledge to an LLM whilst retaining previously-added knowledge. We consider two settings, semi-cooperative and fully-cooperative. Overall, LoRA performs better in most cases than full-fine tuning of all parameters when both new knowledge acquisition and retention of old, including recent, knowledge are taken into account. In the semi-cooperative setting, where datasets are not available after training, MOE mixing, model merging, and LoRA-based orthogonal subspace sequential learning, using a small weight on the orthogonality term, perform well. In the fully-cooperative setting where datasets remain available, joint training and sequential training with replay are both effective approaches with LoRA training generally preferable to full fine-tuning. The codes needed to reproduce the results are provided in an open source repository.","url_abs":"https://arxiv.org/abs/2410.14753v2","url_pdf":"https://arxiv.org/pdf/2410.14753v2.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":"collaboratively-adding-new-knowledge-to-an","repo_url":"https://github.com/RhuiDih/cl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"moe","method_name":"MoE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}