{"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/what-prompts-don-t-say-understanding-and","title":"What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts","arxiv_id":"2505.13360","date":"2025-05-19","proceeding":null,"authors":["Chenyang Yang","Yike Shi","Qianou Ma","Michael Xieyang Liu","Christian Kästner","Tongshuang Wu"],"abstract":"Building LLM-powered software requires developers to communicate their requirements through natural language, but developer prompts are frequently underspecified, failing to fully capture many user-important requirements. In this paper, we present an in-depth analysis of prompt underspecification, showing that while LLMs can often (41.1%) guess unspecified requirements by default, such behavior is less robust: Underspecified prompts are 2x more likely to regress over model or prompt changes, sometimes with accuracy drops by more than 20%. We then demonstrate that simply adding more requirements to a prompt does not reliably improve performance, due to LLMs' limited instruction-following capabilities and competing constraints, and standard prompt optimizers do not offer much help. To address this, we introduce novel requirements-aware prompt optimization mechanisms that can improve performance by 4.8% on average over baselines that naively specify everything in the prompt. Beyond prompt optimization, we envision that effectively managing prompt underspecification requires a broader process, including proactive requirements discovery, evaluation, and monitoring.","url_abs":"https://arxiv.org/abs/2505.13360v1","url_pdf":"https://arxiv.org/pdf/2505.13360v1.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":"what-prompts-don-t-say-understanding-and","repo_url":"https://github.com/malusamayo/underspec-analysis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2505.13360","atlas_url":"https://app.syntology.ai/?focus=2505.13360","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}