# Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting

arXiv: https://arxiv.org/abs/2304.11686 · HTML: https://mlsanity.com/paper/2304.11686/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2023.

## Built on by (most cited first, 23 of 23)

- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [Large Language Models for Cyber Security: A Systematic Literature Review](https://mlsanity.com/paper/2405.04760/) (2024)
- [Using Large Language Models to Generate JUnit Tests: An Empirical Study](https://mlsanity.com/paper/2305.00418/) (2023)
- [LLMs in Software Security: A Survey of Vulnerability Detection Techniques and Insights](https://mlsanity.com/paper/2502.07049/) (2025)
- [Automatically Generating UI Code from Screenshot: A Divide-and-Conquer-Based Approach](https://mlsanity.com/paper/2406.16386/) (2024)
- [Agentic Bug Reproduction for Effective Automated Program Repair at Google](https://mlsanity.com/paper/2502.01821/) (2025)
- [Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency](https://mlsanity.com/paper/2402.15481/) (2024)
- [LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs](https://mlsanity.com/paper/2404.10304/) (2024)
- [Output Format Biases in the Evaluation of Large Language Models for Code Translation](https://mlsanity.com/paper/2403.17214/) (2024)
- [When Fuzzing Meets LLMs: Challenges and Opportunities](https://mlsanity.com/paper/2404.16297/) (2024)
- [FLAG: Finding Line Anomalies (in code) with Generative AI](https://mlsanity.com/paper/2306.12643/) (2023)
- [MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms](https://mlsanity.com/paper/2502.06556/) (2025)
- [Functional Consistency of LLM Code Embeddings: A Self-Evolving Data Synthesis Framework for Benchmarking](https://mlsanity.com/paper/2508.19558/) (2025)
- [Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinement](https://mlsanity.com/paper/2502.17442/) (2024)
- [ZS4C: Zero-Shot Synthesis of Compilable Code for Incomplete Code Snippets using LLMs](https://mlsanity.com/paper/2401.14279/) (2024)
- [Generative transformations and patterns in LLM-native approaches for software verification and falsification](https://mlsanity.com/paper/2404.09384/) (2024)
- [Highlighting Case Studies in LLM Literature Review of Interdisciplinary System Science](https://mlsanity.com/paper/2503.16515/) (2025)
- [Leveraging Large Language Models for Command Injection Vulnerability Analysis in Python: An Empirical Study on Popular Open-Source Projects](https://mlsanity.com/paper/2505.15088/) (2025)
- [Empirical Study of Code Large Language Models for Binary Security Patch Detection](https://mlsanity.com/paper/2509.06052/) (2025)
- [Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques](https://mlsanity.com/paper/2507.13629/) (2025)
- [Multi-Large Language Model Orchestrated Severity Assessment of Clinical Records (MOSAIC)](https://mlsanity.com/paper/2607.05032/) (2026)
- [Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests](https://mlsanity.com/paper/2607.22883/) (2026)
- [WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses](https://mlsanity.com/paper/2609.36635/) (2026)

## Abstract (arXiv)

Automatically detecting software failures is an important task and a longstanding challenge. It requires finding failure-inducing test cases whose test input can trigger the software's fault, and constructing an automated oracle to detect the software's incorrect behaviors. Recent advancement of large language models (LLMs) motivates us to study how far this challenge can be addressed by ChatGPT, a state-of-the-art LLM. Unfortunately, our study shows that ChatGPT has a low probability (28.8%) of finding correct failure-inducing test cases for buggy programs. A possible reason is that finding failure-inducing test cases requires analyzing the subtle code differences between a buggy program and its correct version. When these two versions have similar syntax, ChatGPT is weak at recognizing subtle code differences. Our insight is that ChatGPT's performance can be substantially enhanced when ChatGPT is guided to focus on the subtle code difference. We have an interesting observation that ChatGPT is effective in inferring the intended behaviors of a buggy program. The intended behavior can be leveraged to synthesize programs, in order to make the subtle code difference between a buggy program and its correct version (i.e., the synthesized program) explicit. Driven by this observation, we propose a novel approach that synergistically combines ChatGPT and differential testing to find failure-inducing test cases. We evaluate our approach on Quixbugs (a benchmark of buggy programs), and compare it with state-of-the-art baselines, including direct use of ChatGPT and Pynguin. The experimental result shows that our approach has a much higher probability (77.8%) of finding correct failure-inducing test cases, 2.7X as the best baseline.