Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Automated detection of software failures is an important but challenging software engineering task. It involves finding in a vast search space the failure-inducing test cases that contain an input triggering the software fault and an oracle asserting the incorrect execution. We are motivated to study how far this outstanding challenge can be solved by recent advances in large language models (LLMs) such as ChatGPT. However, our study reveals that ChatGPT has a relatively low success rate (28.8%) in finding correct failure-inducing test cases for buggy programs. A possible conjecture is that finding failure-inducing test cases requires analyzing the subtle differences (nuances) between the tokens of a program's correct version and those for its buggy version. When these two versions have similar sets of tokens and attentions, ChatGPT is weak in distinguishing their differences. We find that ChatGPT can successfully generate failure-inducing test cases when it is guided to focus on the nuances. Our solution is inspired by an interesting observation that ChatGPT could infer the intended functionality of buggy code if it is similar to the correct version. Driven by the inspiration, we develop a novel technique, called Differential Prompting, to effectively find failure-inducing test cases with the help of the compilable code synthesized by the inferred intention. Prompts are constructed based on the nuances between the given version and the synthesized code. We evaluate Differential Prompting on Quixbugs (a popular benchmark of buggy programs) and recent programs published at Codeforces (a popular programming contest portal, which is also an official benchmark of ChatGPT). We compare Differential Prompting with two baselines constructed using conventional ChatGPT prompting and Pynguin (the state-of-the-art unit test generation tool for Python programs). Our evaluation results show that for programs of Quixbugs, Differential Prompting can achieve a success rate of 75.0% in finding failure-inducing test cases, outperforming the best baseline by 2.6X. For programs of Codeforces, Differential Prompting's success rate is 66.7%, outperforming the best baseline by 4.0X.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Qualitative Inquiry and Research Design: Choosing Among Five Approaches
Lewis, S. (2015) · Health Promotion Practice · doi:10.1177/1524839915580941 · Cited by 22,105
Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022) · CHI Conference on Human Factors in Computing Systems Extended Abstracts · doi:10.1145/3491101.3519665 · Cited by 660
Automated Program Repair in the Era of Large Pre-trained Language Models
Xia, C. S., Wei, Y., & Zhang, L. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00129 · Cited by 433
Liu, J., Xia, C. S., Wang, Y., & Zhang, L. (2023) · arXiv · doi:10.48550/arxiv.2305.01210 · Cited by 390 · cited 2×
“Second, recent studies [25], [4], [26] show that ChatGPT has potential in performing various software engineering tasks for Python programs.”
BackgroundSelf-citationLiu, J., Xia, C. S., Wang, Y., & Zhang, L. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-0943 · Cited by 384 · cited 2×
“Second, recent studies [25], [4], [26] show that ChatGPT has potential in performing various software engineering tasks for Python programs.”
BackgroundSelf-citationSemantics-Aware BERT for Language Understanding
Zhang, Z., Wu, Y., Zhao, H., Li, Z., Zhang, S., Zhou, X., & Zhou, X. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6510 · Cited by 364
ChatGPT and Software Testing Education: Promises & Perils
Jalil, S., Rafi, S., LaToza, T. D., Moran, K., & Lam, W. (2023) · 2023 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW) · doi:10.1109/icstw58534.2023.00078 · Cited by 270 · cited 1×
“There are also other works studying ChatGPT’s (or other LLMs’) capabilities for various software engineering tasks, including bug repair [25], [3], fuzzing [22], code generation [51], [52], code summarization [53], software testing education [54], and vulnerability detection [55], [56].”
BackgroundQuixBugs: a multi-lingual program repair benchmark set based on the quixey challenge
Lin, D., Koppel, J., Chen, A., & Solar-Lezama, A. (2017) · Proceedings Companion of the 2017 ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications: Software for Humanity · doi:10.1145/3135932.3135941 · Cited by 242
Few-shot training LLMs for project-specific code-summarization
Ahmed, T., & Devanbu, P. (2022) · Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering · doi:10.1145/3551349.3559555 · Cited by 240 · cited 1×
“There are also other works studying ChatGPT’s (or other LLMs’) capabilities for various software engineering tasks, including bug repair [25], [3], fuzzing [22], code generation [51], [52], code summarization [53], software testing education [54], and vulnerability detection [55], [56].”
BackgroundWidyasari, R., Sim, S. Q., Lok, C., Qi, H., Phan, J., Tay, Q., Tan, C., Wee, F., Tan, J. E., Yieh, Y., et al. (2020) · Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering · doi:10.1145/3368089.3417943 · Cited by 150 · cited 1×
“First, Python is one of the most popular programming languages [24].”
Background
Cited by
Software Testing With Large Language Models: Survey, Landscape, and Vision
Wang, J., Huang, Y., Chen, C., Liu, Z., Wang, S., & Wang, Q. (2024) · IEEE Transactions on Software Engineering · doi:10.1109/tse.2024.3368208 · Cited by 573
“Tu et al. [86] propose LLM4CBI to tame LLMs to generate effective test programs for finding suspicious files.”
Are “Solved Issues” in SWE-bench Really Solved Correctly? An Empirical Study
Wang, Y., Pradel, M., & Liu, Z. (2026) · Proceedings of the 2026 IEEE/ACM 48th International Conference on Software Engineering · doi:10.1145/3744916.3764576 · Cited by 98
“We envision PatchDiff to be useful for building a sustainable and robust patch validation ecosystem for assessing issue-solving tools.”
Self-citationJaffal, N. O., Alkhanafseh, M., & Mohaisen, D. (2025) · AI · doi:10.3390/ai6090216 · Cited by 69
On the Use of ChatGPT for Code Review: Do Developers Like Reviews By ChatGPT?
Watanabe, M., Kashiwa, Y., Lin, B., Hirao, T., Yamaguchi, K., & Iida, H. (2024) · Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering · doi:10.1145/3661167.3661183 · Cited by 28
Metadata
- Authors
- Li, T.-O., Zong, W., Wang, Y., Tian, H., Wang, Y., Cheung, S.-C., & Kramer, J.
- Venue
- 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE)
- Publisher
- IEEE
- Published
- 2023-09-11
- Pages
- 14-26
- OpenAlex
- W4388483640
- Cited by
- 57
- References
- 12
- FWCI
- 11.41
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting. https://app.cochat.ai/papers/10.1109/ase56229.2023.00089
- The paper
- Li, T.-O., Zong, W., Wang, Y., Tian, H., Wang, Y., Cheung, S.-C., & Kramer, J. (2023). Nuances are the Key: Unlocking ChatGPT to Find Failure-Inducing Tests with Differential Prompting. 2023 38th IEEE/ACM International Conference on Automated Software Engineering (ASE). https://doi.org/10.1109/ase56229.2023.00089
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.