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

arXiv: https://arxiv.org/abs/2505.13360 · HTML: https://mlsanity.com/paper/2505.13360/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 67 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 30 of 37)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Multitask Prompted Training Enables Zero-Shot Task Generalization](https://mlsanity.com/paper/2110.08207/) (2021)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [Enhancing Chat Language Models by Scaling High-quality Instructional Conversations](https://mlsanity.com/paper/2305.14233/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [Cross-Task Generalization via Natural Language Crowdsourcing Instructions](https://mlsanity.com/paper/2104.08773/) (2021)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [Stress Test Evaluation for Natural Language Inference](https://mlsanity.com/paper/1806.00692/) (2018)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [InFoBench: Evaluating Instruction Following Ability in Large Language Models](https://mlsanity.com/paper/2401.03601/) (2024)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs](https://mlsanity.com/paper/2311.09469/) (2023)
- [Which Economic Tasks are Performed with AI? Evidence from Millions of Claude Conversations](https://mlsanity.com/paper/2503.04761/) (2025)
- [CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models](https://mlsanity.com/paper/2212.07769/) (2022)
- [Shopping Queries Dataset: A Large-Scale ESCI Benchmark for Improving Product Search](https://mlsanity.com/paper/2206.06588/) (2022)
- [Aligning Language Models to Explicitly Handle Ambiguity](https://mlsanity.com/paper/2404.11972/) (2024)
- [CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models](https://mlsanity.com/paper/2405.12063/) (2024)
- [On the Worst Prompt Performance of Large Language Models](https://mlsanity.com/paper/2406.10248/) (2024)
- [Ambig-SWE: Interactive Agents to Overcome Underspecificity in Software Engineering](https://mlsanity.com/paper/2502.13069/) (2025)
- [Idiosyncrasies in Large Language Models](https://mlsanity.com/paper/2502.12150/) (2025)
- [SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning](https://mlsanity.com/paper/2407.12874/) (2024)
- [EvalTree: Profiling Language Model Weaknesses via Hierarchical Capability Trees](https://mlsanity.com/paper/2503.08893/) (2025)
- [What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Use](https://mlsanity.com/paper/2409.08775/) (2024)
- [(Why) Is My Prompt Getting Worse? Rethinking Regression Testing for Evolving LLM APIs](https://mlsanity.com/paper/2311.11123/) (2023)
- [Prompts Are Programs Too! Understanding How Developers Build Software Containing Prompts](https://mlsanity.com/paper/2409.12447/) (2024)

## Built on by (most cited first, 30 of 32)

- [Flipping the Dialogue: Training and Evaluating User Language Models](https://mlsanity.com/paper/2510.06552/) (2025)
- [AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition](https://mlsanity.com/paper/2602.11348/) (2026)
- [Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions](https://mlsanity.com/paper/2602.14878/) (2026)
- [When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents](https://mlsanity.com/paper/2602.08235/) (2026)
- [Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants](https://mlsanity.com/paper/2605.09808/) (2026)
- [Reframing LLM Agent Security as an Agent-Human Interaction Problem](https://mlsanity.com/paper/2605.24309/) (2026)
- [CoBRA: Programming Cognitive Bias in Social Agents Using Classic Social Science Experiments](https://mlsanity.com/paper/2509.13588/) (2025)
- [A Taxonomy of Prompt Defects in LLM Systems](https://mlsanity.com/paper/2509.14404/) (2025)
- [Beyond the Prompt: An Empirical Study of Cursor Rules](https://mlsanity.com/paper/2512.18925/) (2025)
- [Better Harnesses, Smaller Models: Building 90% Cheaper Agents via Automated Harness Adaptation](https://mlsanity.com/paper/2607.08938/) (2026)
- [Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments](https://mlsanity.com/paper/2605.27209/) (2026)
- [Safeguarding LLM Agents from Misalignment through Provenance Analysis](https://mlsanity.com/paper/2607.01236/) (2026)
- [From Anatomy to Smells: An Empirical Study of SKILL.md in Agent Skills](https://mlsanity.com/paper/2607.01456/) (2026)
- [The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning](https://mlsanity.com/paper/2601.14127/) (2026)
- [Ambiguity Collapse by LLMs: A Taxonomy of Epistemic Risks](https://mlsanity.com/paper/2603.05801/) (2026)
- [Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations](https://mlsanity.com/paper/2604.27093/) (2026)
- [Consistency as a Testable Property: Statistical Methods to Evaluate AI Agent Reliability](https://mlsanity.com/paper/2605.10516/) (2026)
- [From Articles to Code: On-Demand Generation of Core Algorithms from Scientific Publications](https://mlsanity.com/paper/2507.22324/) (2025)
- [The Anatomy of Uncertainty in LLMs](https://mlsanity.com/paper/2603.24967/) (2026)
- [Don't Make Models Guess Security and Safety: Symbolic Guardrails for Domain-Specific AI Agents](https://mlsanity.com/paper/2604.15579/) (2026)
- [Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering](https://mlsanity.com/paper/2607.01087/) (2026)
- [Power and Limitations of Aggregation in Compound AI Systems](https://mlsanity.com/paper/2602.21556/) (2026)
- [AnnoBench: A Benchmark for Visualization Annotation Generation](https://mlsanity.com/paper/2607.25911/) (2026)
- [Position: Intelligent Coding Systems Should Write Programs with Justifications](https://mlsanity.com/paper/2508.06017/) (2025)
- [Reasoning With a Star: A Heliophysics Dataset and Benchmark for Agentic Scientific Reasoning](https://mlsanity.com/paper/2511.20694/) (2025)
- [Exploring Human-in-the-Loop Themes in AI Application Development: An Empirical Thematic Analysis](https://mlsanity.com/paper/2603.05510/) (2026)
- [StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation](https://mlsanity.com/paper/2604.14631/) (2026)
- [Instruction Complexity Induces Positional Collapse in Adversarial LLM Evaluation](https://mlsanity.com/paper/2604.27249/) (2026)
- [Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution](https://mlsanity.com/paper/2606.05486/) (2026)
- [NL-PAC: Specification Ambiguity and Certified Minimax Risk Floors in LLM-Mediated Supervision](https://mlsanity.com/paper/2607.08961/) (2026)

## Abstract (arXiv)

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.