An official website of the United States government
Abstract Automatic Program Repair (APR) has garnered significant attention as a practical research domain focused on automatically fixing bugs in programs. While existing APR techniques primarily target imperative programming languages like C and Java, there is a growing need for effective solutions applicable to declarative software specification languages. This paper systematically investigates the capacity of Large Language Models (LLMs) to repair declarative specifications in Alloy, a declarative formal language used for software specification. We designed six different repair settings, encompassing single-agent and dual-agent paradigms, utilizing various LLMs. These configurations also incorporate different levels of feedback, including an auto-prompting mechanism for generating prompts autonomously using LLMs. Our study reveals that dual-agent with auto-prompting setup outperforms the other settings, albeit with a marginal increase in the number of iterations and token usage. This dual-agent setup demonstrated superior effectiveness compared to state-of-the-art Alloy APR techniques when evaluated on a comprehensive set of benchmarks. This work is the first to empirically evaluate LLM capabilities to repair declarative specifications, while taking into account recent trending LLM concepts such as LLM-based agents, feedback, auto-prompting, and tools, thus paving the way for future agent-based techniques in software engineering.
more »
« less
This content will become publicly available on March 22, 2026
Automated Program Repair: Emerging Trends Pose and Expose Problems for Benchmarks
Machine learning (ML) pervades the field of Automated Program Repair (APR). Algorithms deploy neural machine translation and large language models (LLMs) to generate software patches, among other tasks. But, there are important differences between these applications of ML and earlier work, which complicates the task of ensuring that results are valid and likely to generalize. A challenge is that the most popular APR evaluation benchmarks were not designed with ML techniques in mind. This is especially true for LLMs, whose large and often poorly-disclosed training datasets may include problems on which they are evaluated. This article reviews work in APR published in the field’s top five venues since 2018, emphasizing emerging trends in the field, including the dramatic rise of ML models, including LLMs. ML-based articles are categorized along structural and functional dimensions, and a variety of issues are identified that these new methods raise. Importantly, data leakage and contamination concerns arise from the challenge of validating ML-based APR using existing benchmarks, which were designed before these techniques were popular. We discuss inconsistencies in evaluation design and performance reporting and offer pointers to solutions where they are available. Finally, we highlight promising new directions that the field is already taking.
more »
« less
- PAR ID:
- 10634726
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Computing Surveys
- Volume:
- 57
- Issue:
- 8
- ISSN:
- 0360-0300
- Page Range / eLocation ID:
- 1 to 18
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Large Language Models (LLMs) have generated considerable interest and debate regarding their potential emergence of Theory of Mind (ToM). Several recent inquiries reveal a lack of robust ToM in these models and pose a pressing demand to develop new benchmarks, as current ones primarily focus on different aspects of ToM and are prone to shortcuts and data leakage. In this position paper, we seek to answer two road-blocking questions: (1) How can we taxonomize a holistic landscape of machine ToM? (2) What is a more effective evaluation protocol for machine ToM? Following psychological studies, we taxonomize machine ToM into 7 mental state categories and delineate existing benchmarks to identify under-explored aspects of ToM. We argue for a holistic and situated evaluation of ToM to break ToM into individual components and treat LLMs as an agent who is physically situated in environments and socially situated in interactions with humans. Such situated evaluation provides a more comprehensive assessment of mental states and potentially mitigates the risk of shortcuts and data leakage. We further present a pilot study in a grid world setup as a proof of concept. We hope this position paper can facilitate future research to integrate ToM with LLMs and offer an intuitive means for researchers to better position their work in the landscape of ToM.more » « less
-
Automated Program Repair (APR) is one of the most recent advances in automated debugging, and can directly fix buggy programs with minimal human intervention. Although various advanced APR techniques (including search-based or semantic-based ones) have been proposed, they mainly work at the source-code level and it is not clear how bytecode-level APR performs in practice. Also, empirical studies of the existing techniques on bugs beyond what has been reported in the original papers are rather limited. In this paper, we implement the first practical bytecode-level APR technique, PraPR, and present the first extensive study on fixing real-world bugs (e.g., Defects4J bugs) using JVM bytecode mutation. The experimental results show that surprisingly even PraPR with only the basic traditional mutators can produce genuine fixes for 17 bugs; with simple additional commonly used APR mutators, PraPR is able to produce genuine fixes for 43 bugs, significantly outperforming state-of-the-art APR, while being over 10X faster. Furthermore, we performed an extensive study of PraPR and other recent APR tools on a large number of additional real-world bugs, and demonstrated the overfitting problem of recent advanced APR tools for the first time. Lastly, PraPR has also successfully fixed bugs for other JVM languages (e.g., for the popular Kotlin language), indicating PraPR can greatly complement existing source-code-level APR.more » « less
-
Abstract The number and dynamic nature of web sites and mobile applications present regulators and app store operators with significant challenges when it comes to enforcing compliance with applicable privacy and data protection laws. Over the past several years, people have turned to Natural Language Processing (NLP) techniques to automate privacy compliance analysis (e.g., comparing statements in privacy policies with analysis of the code and behavior of mobile apps) and to answer people’s privacy questions. Traditionally, these NLP techniques have relied on labor-intensive and potentially error-prone manual annotation processes to build the corpora necessary to train them. This article explores and evaluates the use of Large Language Models (LLMs) as an alternative for effectively and efficiently identifying and categorizing a variety of data practice disclosures found in the text of privacy policies. Specifically, we report on the performance of ChatGPT and Llama 2, two particularly popular LLM-based tools. This includes engineering prompts and evaluating different configurations of these LLM techniques. Evaluation of the resulting techniques on well-known corpora of privacy policy annotations yields an F1 score exceeding 93%. This score is higher than scores reported earlier in the literature on these benchmarks. This performance is obtained at minimal marginal cost (excluding the cost required to train the foundational models themselves). These results, which are consistent with those reported in other domains, suggest that LLMs offer a particularly promising approach to automated privacy policy analysis at scale.more » « less
-
null (Ed.)Machine Learning has become a popular tool in a variety of applications in criminal justice, including sentencing and policing. Media has brought attention to the possibility of predictive policing systems causing disparate impacts and exacerbating social injustices. However, there is little academic research on the importance of fairness in machine learning applications in policing. Although prior research has shown that machine learning models can handle some tasks efficiently, they are susceptible to replicating systemic bias of previous human decision-makers. While there is much research on fair machine learning in general, there is a need to investigate fair machine learning techniques as they pertain to the predictive policing. Therefore, we evaluate the existing publications in the field of fairness in machine learning and predictive policing to arrive at a set of standards for fair predictive policing. We also review the evaluations of ML applications in the area of criminal justice and potential techniques to improve these technologies going forward. We urge that the growing literature on fairness in ML be brought into conversation with the legal and social science concerns being raised about predictive policing. Lastly, in any area, including predictive policing, the pros and cons of the technology need to be evaluated holistically to determine whether and how the technology should be used in policing.more » « less
