{"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/the-art-of-llm-refinement-ask-refine-and","title":"The ART of LLM Refinement: Ask, Refine, and Trust","arxiv_id":"2311.07961","date":"2023-11-14","proceeding":null,"authors":["Kumar Shridhar","Koustuv Sinha","Andrew Cohen","Tianlu Wang","Ping Yu","Ram Pasunuru","Mrinmaya Sachan","Jason Weston","Asli Celikyilmaz"],"abstract":"In recent years, Large Language Models (LLMs) have demonstrated remarkable generative abilities, but can they judge the quality of their own generations? A popular concept, referred to as self-refinement, postulates that LLMs can detect and correct the errors in their generations when asked to do so. However, recent empirical evidence points in the opposite direction, suggesting that LLMs often struggle to accurately identify errors when reasoning is involved. To address this, we propose a reasoning with refinement objective called ART: Ask, Refine, and Trust, which asks necessary questions to decide when an LLM should refine its output, and either affirm or withhold trust in its refinement by ranking the refinement and the initial prediction. On two multistep reasoning tasks of mathematical word problems (GSM8K) and question answering (StrategyQA), ART achieves a performance gain of +5 points over self-refinement baselines, while using a much smaller model as the decision maker. We also demonstrate the benefit of using smaller models to make refinement decisions as a cost-effective alternative to fine-tuning a larger model.","url_abs":"https://arxiv.org/abs/2311.07961v1","url_pdf":"https://arxiv.org/pdf/2311.07961v1.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":[],"tasks":[{"task_slug":"arithmetic-reasoning","task_name":"Arithmetic Reasoning"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"strategyqa","task_name":"StrategyQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/arithmetic-reasoning-on-gsm8k","task":"Arithmetic Reasoning","dataset":"GSM8K","model":"ChatGPT (Ask, Refine, Trust)","rank_in_archive_order":58,"of":164,"metrics":{"Accuracy":"82.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2311.07961","atlas_url":"https://app.syntology.ai/?focus=2311.07961","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}