{"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/verdict-a-library-for-scaling-judge-time","title":"Verdict: A Library for Scaling Judge-Time Compute","arxiv_id":"2502.18018","date":"2025-02-25","proceeding":null,"authors":["Nimit Kalra","Leonard Tang"],"abstract":"The use of LLMs as automated judges (\"LLM-as-a-judge\") is now widespread, yet standard judges suffer from a multitude of reliability issues. To address these challenges, we introduce Verdict, an open-source library for scaling judge-time compute to enhance the accuracy, reliability, and interpretability of automated evaluators. Verdict leverages the composition of modular reasoning units -- such as verification, debate, and aggregation -- and increased inference-time compute to improve LLM judge quality. Across a variety of challenging tasks such as content moderation, fact-checking, and hallucination detection, Verdict judges achieve state-of-the-art (SOTA) or near-SOTA performance, surpassing orders-of-magnitude larger fine-tuned judges, prompted judges, and reasoning models. Ultimately, we hope Verdict serves as a useful framework for researchers and practitioners building scalable, interpretable, and reliable LLM-based evaluators.","url_abs":"https://arxiv.org/abs/2502.18018v1","url_pdf":"https://arxiv.org/pdf/2502.18018v1.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":"verdict-a-library-for-scaling-judge-time","repo_url":"https://github.com/haizelabs/verdict","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"hallucination","task_name":"Hallucination"}],"methods":[{"method_slug":null,"method_name":"Library"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.18018","atlas_url":"https://app.syntology.ai/?focus=2502.18018","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}