Using LLMs to Extract OCL Specifications from Java and Python Programs:An Empirical Study
Saved in:
| Title: | Using LLMs to Extract OCL Specifications from Java and Python Programs:An Empirical Study |
|---|---|
| Authors: | Siala, Hanan, Lano, Kevin |
| Source: | Siala, H & Lano, K 2025, 'Using LLMs to Extract OCL Specifications from Java and Python Programs : An Empirical Study', CEUR Workshop Proceedings, vol. 4122. |
| Publication Year: | 2025 |
| Collection: | King's College, London: Research Portal |
| Subject Terms: | Object Constraint Language (OCL), Machine Learning, Large Language Models (LLMs), Reverse engineering, Java programs, Python programs |
| Description: | This paper presents a comprehensive study of the application of several open-source Large Language Models (LLMs) for abstracting Object Constraint Language (OCL) specifications from source code. We aim to provide researchers and developers with insights into the capabilities and limitations of using different LLMs to abstract OCL specifications from code. We evaluate a collection of open-source LLMs of comparable size (StarCoder2, LLaMA, CodeLlama, Mistral, and DeepSeek) by prompting them to generate OCL specifications for both Java and Python programs. The results show that both Mistral and DeepSeek outperform other LLMs in abstracting OCL specifications from both languages. |
| Document Type: | article in journal/newspaper |
| File Description: | application/pdf |
| Language: | English |
| Availability: | https://kclpure.kcl.ac.uk/portal/en/publications/1badd32b-4bb5-4104-8a41-f0d7543d96bc https://kclpure.kcl.ac.uk/ws/files/362382813/Using_LLMs_to_extract_OCL_specifications_from_Java_and_Python_programs_Version_of_Record.pdf https://ceur-ws.org/Vol-4122/ |
| Rights: | info:eu-repo/semantics/openAccess ; http://creativecommons.org/licenses/by/4.0/ |
| Accession Number: | edsbas.B08DF974 |
| Database: | BASE |
Nájsť tento článok vo Web of Science | Abstract: | This paper presents a comprehensive study of the application of several open-source Large Language Models (LLMs) for abstracting Object Constraint Language (OCL) specifications from source code. We aim to provide researchers and developers with insights into the capabilities and limitations of using different LLMs to abstract OCL specifications from code. We evaluate a collection of open-source LLMs of comparable size (StarCoder2, LLaMA, CodeLlama, Mistral, and DeepSeek) by prompting them to generate OCL specifications for both Java and Python programs. The results show that both Mistral and DeepSeek outperform other LLMs in abstracting OCL specifications from both languages. |
|---|