{"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/unleashing-the-potentials-of-likelihood","title":"Unleashing the Potentials of Likelihood Composition for Multi-modal Language Models","arxiv_id":"2410.00363","date":"2024-10-01","proceeding":null,"authors":["Shitian Zhao","Renrui Zhang","Xu Luo","Yan Wang","Shanghang Zhang","Peng Gao"],"abstract":"Model fusing has always been an important topic, especially in an era where large language models (LLM) and multi-modal language models (MLM) with different architectures, parameter sizes and training pipelines, are being created all the time. In this work, we propose a post-hoc framework, aiming at fusing heterogeneous models off-the-shell, which we call \\textit{likelihood composition}, and the basic idea is to compose multiple models' likelihood distribution when doing a multi-choice visual-question-answering task. Here the core concept, \\textit{likelihood}, is actually the log-probability of the candidate answer. In \\textit{likelihood composition}, we introduce some basic operations: \\textit{debias}, \\textit{highlight}, \\textit{majority-vote} and \\textit{ensemble}. By combining (composing) these basic elements, we get the mixed composition methods: \\textit{mix-composition}. Through conducting comprehensive experiments on 9 VQA datasets and 10 MLMs, we prove the effectiveness of \\textit{mix-composition} compared with simple \\textit{ensemble} or \\textit{majority-vote} methods. In this framework, people can propose new basic composition methods and combine them to get the new mixed composition methods. We hope our proposed \\textit{likelihood composition} can provide a new perspective of fusing heterogeneous models and inspire the exploration under this framework.","url_abs":"https://arxiv.org/abs/2410.00363v1","url_pdf":"https://arxiv.org/pdf/2410.00363v1.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":"unleashing-the-potentials-of-likelihood","repo_url":"https://github.com/zhaoshitian/Likelihood-Composition-Toolkit","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}