Happy Open Access Week from arXiv! YOU make open access possible! Tell us why you support #openaccess and give to arXiv this week to help keep science open for all. Donate! Skip to main content We gratefully acknowledge support from the Simons Foundation, member institutions , and all contributors. Donate > cs > arXiv:2407.21787 Help | Advanced Search All fields Title Author Abstract Comments Journal reference ACM classification MSC classification Report number arXiv identifier DOI ORCID arXiv author ID Help pages Full text Search open search GO open navigation menu quick links Login Help Pages About --> Computer Science > Machine Learning arXiv:2407.21787 (cs) [Submitted on 31 Jul 2024 ( v1 ), last revised 30 Dec 2024 (this version, v3)] Title: Large Language Monkeys: Scaling Inference Compute with Repeated Sampling Authors: Bradley Brown , Jordan Juravsky , Ryan Ehrlich , Ronald Clark , Quoc V. Le , Christopher Ré , Azalia Mirhoseini View a PDF of the paper titled Large Language Monkeys: Scaling Inference Compute with Repeated Sampling, by Bradley Brown and 6 other authors View PDF HTML (experimental) Abstract: Scaling the amount of compute used to train language models has dramatically improved their capabilities. However, when it comes to inference, we often limit models to making only one attempt at a problem. Here, we explore inference compute as another axis for scaling, using the simple technique of repeatedly sampling candidate solutions from a model. Across multiple tasks and models, we observe that coverage -- the fraction of problems that are solved by any generated sample -- scales with the number of samples over four orders of magnitude. Interestingly, the relationship between coverage and the number of samples is often log-linear and can be modelled with an exponentiated power law, suggesting the existence of inference-time scaling laws. In domains like coding and formal proofs, where answers can be automatically verified, these increases in coverage directly translate into improved performance. When we apply repeated sampling to SWE-bench Lite, the fraction of issues solved with DeepSeek-Coder-V2-Instruct increases from 15.9% with one sample to 56% with 250 samples, outperforming the single-sample state-of-the-art of 43%. In domains without automatic verifiers, we find that common methods for picking from a sample collection (majority voting and reward models) plateau beyond several hundred samples and fail to fully scale with the sample budget. Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2407.21787 [cs.LG] (or arXiv:2407.21787v3 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2407.21787 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Bradley Brown [ view email ] [v1] Wed, 31 Jul 2024 17:57:25 UTC (592 KB) [v2] Mon, 16 Sep 2024 17:58:42 UTC (405 KB) [v3] Mon, 30 Dec 2024 19:03:24 UTC (405 KB) Full-text links: Access Paper: View a PDF of the paper titled Large Language Monkeys: Scaling Inference Compute with Repeated Sampling, by Bradley Brown and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2024-07 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation &times; loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) Links to Code Toggle Papers with Code ( What is Papers with Code? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both 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. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) About Help contact arXiv Click here to contact arXiv Contact subscribe to arXiv mailings Click here to subscribe Subscribe Copyright Privacy Policy Web Accessibility Assistance arXiv Operational Status