# When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions

arXiv: https://arxiv.org/abs/2507.20439 · HTML: https://mlsanity.com/paper/2507.20439/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 27 Jul 2025.

## Builds on (most cited first, 16 of 16)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Measuring Coding Challenge Competence With APPS](https://mlsanity.com/paper/2105.09938/) (2021)
- [DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation](https://mlsanity.com/paper/2211.11501/) (2022)
- [Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributions](https://mlsanity.com/paper/2108.09293/) (2021)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [GitHub Copilot AI pair programmer: Asset or Liability?](https://mlsanity.com/paper/2206.15331/) (2022)
- [Towards an Understanding of Large Language Models in Software Engineering Tasks](https://mlsanity.com/paper/2308.11396/) (2023)
- [LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?](https://mlsanity.com/paper/2506.11928/) (2025)
- [What's Wrong with Your Code Generated by Large Language Models? An Extensive Study](https://mlsanity.com/paper/2407.06153/) (2024)
- [DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructions](https://mlsanity.com/paper/2312.04730/) (2023)
- [Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation](https://mlsanity.com/paper/2306.01183/) (2023)
- [HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent](https://mlsanity.com/paper/2406.00215/) (2024)
- [Software Effort Estimation Accuracy Prediction of Machine Learning Techniques: A Systematic Performance Evaluation](https://mlsanity.com/paper/2101.10658/) (2021)
- [Enhancing Software Effort Estimation through Reinforcement Learning-based Project Management-Oriented Feature Selection](https://mlsanity.com/paper/2403.16749/) (2024)

## Built on by (most cited first, 11 of 11)

- [BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions](https://mlsanity.com/paper/2510.05318/) (2025)
- [ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation](https://mlsanity.com/paper/2607.00711/) (2026)
- [Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness](https://mlsanity.com/paper/2510.08238/) (2025)
- [Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis](https://mlsanity.com/paper/2604.24703/) (2026)
- [Measuring LLM Trust Allocation Across Conflicting Software Artifacts](https://mlsanity.com/paper/2604.03447/) (2026)
- [Obey, Diverge, Collapse: Blind Obedience to Incorrect Instructions Drives Code LLMs to Irrecoverable Code Semantic Collapse](https://mlsanity.com/paper/2607.04537/) (2026)
- [Automatically Evolving Prompt Guidelines for Task-Specific Optimization](https://mlsanity.com/paper/2607.14105/) (2026)
- [AssumptionMiner: Extracting, Tracing, and Revising Implicit Assumptions in LLM Code Generation](https://mlsanity.com/paper/2607.22898/) (2026)
- [What Makes Software Issue Resolution Tasks Difficult for Agents?](https://mlsanity.com/paper/2608.18280/) (2026)
- [Beyond the Payload: How User Invocation Shapes Coding Agent Vulnerability to Repository Poisoning](https://mlsanity.com/paper/2608.30686/) (2026)
- [IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications](https://mlsanity.com/paper/2609.10539/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated impressive performance in code generation tasks under idealized conditions, where task descriptions are clear and precise. However, in practice, task descriptions frequently exhibit ambiguity, incompleteness, or internal contradictions. In this paper, we present the first empirical study examining the robustness of state-of-the-art code generation models when faced with such unclear task descriptions. We extend the HumanEval and MBPP benchmarks by systematically introducing realistic task descriptions flaws through guided mutation strategies, producing a dataset that mirrors the messiness of informal developer instructions. We evaluate multiple LLMs of varying sizes and architectures, analyzing their functional correctness and failure modes across task descriptions categories. Our findings reveal that even minor imperfections in task description phrasing can cause significant performance degradation, with contradictory task descriptions resulting in numerous logical errors. Moreover, while larger models tend to be more resilient than smaller variants, they are not immune to the challenges posed by unclear requirements. We further analyze semantic error patterns and identify correlations between description clarity, model behavior, and error types. Our results underscore the critical need for developing LLMs that are not only powerful but also robust to the imperfections inherent in natural user tasks, highlighting important considerations for improving model training strategies, designing more realistic evaluation benchmarks, and ensuring reliable deployment in practical software development environments.