{"ID":6024118,"CreatedAt":"2026-07-08T01:00:23.257252134Z","UpdatedAt":"2026-07-09T19:11:46.74728655Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.05582","arxiv_id":"2607.05582","title":"Prompting Beats Fine-Tuning: Generative Expected Value Scoring for Statutory Term Retrieval","abstract":"Legal concepts in statutes are often expressed using vague terms, and practitioners frequently turn to case law to interpret them. We study the task of ranking case-law sentences by their usefulness for explaining a concept or target statutory term, using an established dataset of 26,959 sentences covering 42 U.S. Code concepts labeled into four explanatory-value categories. We compare two families of methods: (i) supervised fine-tuning of encoder-only models (ModernBERT) and (ii) zero-shot prompting of decoder-only models. We show that across all concepts and standard NDCG cutoffs, ModernBERT largely matches earlier BERT-family baselines. In contrast, prompting decoder-only models achieves the strongest overall effectiveness, with our best system surpassing all previously reported state-of-the-art results on this task.","short_abstract":"Legal concepts in statutes are often expressed using vague terms, and practitioners frequently turn to case law to interpret them. We study the task of ranking case-law sentences by their usefulness for explaining a concept or target statutory term, using an established dataset of 26,959 sentences covering 42 U.S. Code...","url_abs":"https://arxiv.org/abs/2607.05582","url_pdf":"https://arxiv.org/pdf/2607.05582v1","authors":"[\"Alvin Wang\",\"Jaromir Savelka\"]","published":"2026-07-06T19:26:44Z","proceeding":"cs.IR","tasks":"[\"cs.IR\"]","methods":"[]","has_code":false}