@inproceedings{yang-etal-2026-prompts,
    title = "What Prompts Don{'}t Say: Understanding and Managing Underspecification in {LLM} Prompts",
    author = "Yang, Chenyang  and
      Shi, Yike  and
      Ma, Qianou  and
      Liu, Michael Xieyang  and
      Kaestner, Christian  and
      Wu, Tongshuang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.441/",
    pages = "9072--9101",
    ISBN = "979-8-89176-395-1",
    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."
}