What Prompts Don’t Say: Understanding and Managing Underspecification in LLM Prompts

ACL ARR 2026 January Submission5910 Authors

Keywords: underspecification, empirical study on LLM behaviors, prompt development

Abstract: Prompt underspecification is a common challenge when interacting with LLMs. In this paper, we present an in-depth analysis of this problem, showing that while LLMs can often infer unspecified requirements by default (41.1%), such behavior is fragile: Under-specified prompts are 2x as likely to regress across model or prompt changes, sometimes with accuracy drops exceeding 20%. This instability makes it difficult to reliably build LLM applications. Moreover, simply specifying all requirements does not consistently help, as models have limited instruction-following ability and requirements can conflict. Standard prompt optimizers likewise provide little benefit. To address these issues, we propose requirements-aware prompt optimization mechanisms that improve performance by 4.8% on average over baselines. We further advocate for a systematic process of proactive requirements discovery, evaluation, and monitoring to better manage prompt underspecification in practice.

Paper Type: Long

Research Area: Language Models

Research Area Keywords: applications, prompting

Contribution Types: NLP engineering experiment, Data analysis

Languages Studied: English

Submission Number: 5910