{"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/tract-regression-aware-fine-tuning-meets","title":"TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge","arxiv_id":"2503.04381","date":"2025-03-06","proceeding":null,"authors":["Cheng-Han Chiang","Hung-Yi Lee","Michal Lukasik"],"abstract":"The LLM-as-a-judge paradigm uses large language models (LLMs) for automated text evaluation, where a numerical assessment is assigned by an LLM to the input text following scoring rubrics. Existing methods for LLM-as-a-judge use cross-entropy (CE) loss for fine-tuning, which neglects the numeric nature of score prediction. Recent work addresses numerical prediction limitations of LLM fine-tuning through regression-aware fine-tuning, which, however, does not consider chain-of-thought (CoT) reasoning for score prediction. In this paper, we introduce TRACT (Two-stage Regression-Aware fine-tuning with CoT), a method combining CoT reasoning with regression-aware training. TRACT consists of two stages: first, seed LLM is fine-tuned to generate CoTs, which serve as supervision for the second stage fine-tuning. The training objective of TRACT combines the CE loss for learning the CoT reasoning capabilities, and the regression-aware loss for the score prediction. Experiments across four LLM-as-a-judge datasets and two LLMs show that TRACT significantly outperforms existing methods. Extensive ablation studies validate the importance of each component in TRACT.","url_abs":"https://arxiv.org/abs/2503.04381v1","url_pdf":"https://arxiv.org/pdf/2503.04381v1.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":"tract-regression-aware-fine-tuning-meets","repo_url":"https://github.com/d223302/tract","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.04381","atlas_url":"https://app.syntology.ai/?focus=2503.04381","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}