{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T13:53:00Z","timestamp":1764942780496,"version":"3.46.0"},"reference-count":100,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Explanations for static-analysis warnings assist developers in understanding potential code issues. An end-to-end pipeline was implemented to generate natural-language explanations, evaluated on 5183 warning\u2013explanation pairs from Java repositories, including a manually validated gold subset of 1176 examples for faithfulness assessment. Explanations were produced by a transformer-based encoder\u2013decoder model (CodeT5) conditioned on warning types, contextual code snippets, and static-analysis evidence. Initial experiments employed single-objective optimization for hyperparameters (using a genetic algorithm with dynamic search-space correction, which adaptively adjusted search bounds based on the evolving distribution of candidate solutions, clustering promising regions, and pruning unproductive ones), but this approach enforced a fixed faithfulness\u2013fluency trade-off; therefore, a multi-objective evolutionary algorithm (NSGA-II) was adopted to jointly optimize both criteria. Pareto-optimal configurations improved normalized faithfulness by up to 12% and textual quality by 5\u20138% compared to baseline CodeT5 settings, with batch sizes of 10\u201321, learning rates 2.3\u00d710\u22125 to 5\u00d710\u22124, maximum token lengths of 36\u201365, beam width 5, length penalty 1.15, and nucleus sampling p=0.88. Candidate explanations were reranked using a composite score of likelihood, faithfulness, and code-usefulness, producing final outputs in under 0.001 s per example. The results indicate that structured conditioning, evolutionary hyperparameter search, and reranking yield explanations that are both aligned with static-analysis evidence and linguistically coherent.<\/jats:p>","DOI":"10.3390\/computers14120534","type":"journal-article","created":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T13:17:07Z","timestamp":1764940627000},"page":"534","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generation of Natural-Language Explanations for Static-Analysis Warnings Using Single- and Multi-Objective Optimization"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8986-402X","authenticated-orcid":false,"given":"Ivan","family":"Malashin","sequence":"first","affiliation":[{"name":"Artificial Intelligence Technology Scientific and Education Center, Bauman Moscow State Technical University, 105005 Moscow, Russia"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.autcon.2016.08.027","article-title":"Integrating semantic NLP and logic reasoning into a unified system for fully-automated code checking","volume":"73","author":"Zhang","year":"2017","journal-title":"Autom. Constr."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"15217","DOI":"10.1007\/s10462-023-10526-z","article-title":"A comprehensive survey on NSGA-II for multi-objective optimization and applications","volume":"56","author":"Ma","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"22582","DOI":"10.1109\/ACCESS.2024.3362896","article-title":"DP-CCL: A supervised contrastive learning approach using CodeBERT model in software defect prediction","volume":"12","author":"Sahar","year":"2024","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1007\/s10515-025-00543-3","article-title":"MCL-VD: Multi-modal contrastive learning with LoRA-enhanced GraphCodeBERT for effective vulnerability detection","volume":"32","author":"Cao","year":"2025","journal-title":"Autom. Softw. Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"100805","DOI":"10.1109\/ACCESS.2024.3430558","article-title":"Multi-label code error classification using CodeT5 and ML-KNN","volume":"12","author":"Amin","year":"2024","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/s10664-024-10594-x","article-title":"Explainable automated debugging via large language model-driven scientific debugging","volume":"30","author":"Kang","year":"2025","journal-title":"Empir. Softw. Eng."},{"key":"ref_7","first-page":"444","article-title":"Leveraging Large Language Models for Automated Bug Fixing","volume":"15","author":"Alsaedi","year":"2024","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3719351","article-title":"Fully Autonomous Programming Using Iterative Multi-Agent Debugging with Large Language Models","volume":"5","author":"Grishina","year":"2025","journal-title":"ACM Trans. Evol. Learn. Optim."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liventsev, V., Grishina, A., H\u00e4rm\u00e4, A., and Moonen, L. (2023, January 15\u201319). Fully autonomous programming with large language models. Proceedings of the Genetic and Evolutionary Computation Conference, Lisbon, Portugal.","DOI":"10.1145\/3583131.3590481"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Vella Zarb, D., Parks, G., and Kipouros, T. (2024, January 14\u201318). Synergistic Utilization of LLMs for Program Synthesis. Proceedings of the Genetic and Evolutionary Computation Conference Companion, Melbourne, VIC, Australia.","DOI":"10.1145\/3638530.3654426"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s10515-025-00492-x","article-title":"A study on prompt design, advantages and limitations of ChatGPT for deep learning program repair","volume":"32","author":"Cao","year":"2025","journal-title":"Autom. Softw. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1007\/s11227-025-07237-3","article-title":"Evaluating ChatGPT\u2019s strengths and limitations for data race detection in parallel programming via prompt engineering","volume":"81","author":"Alsofyani","year":"2025","journal-title":"J. Supercomput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102250","DOI":"10.1016\/j.softx.2025.102250","article-title":"Introspector: A general-purpose tool for visualizing and comparing runtime object structures on the Java platform","volume":"31","author":"Ortin","year":"2025","journal-title":"SoftwareX"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1111\/2041-210X.14325","article-title":"Harnessing large language models for coding, teaching and inclusion to empower research in ecology and evolution","volume":"15","author":"Cooper","year":"2024","journal-title":"Methods Ecol. Evol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1007\/s10664-022-10189-4","article-title":"Real world projects, real faults: Evaluating spectrum based fault localization techniques on Python projects","volume":"27","author":"Widyasari","year":"2022","journal-title":"Empir. Softw. Eng."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"10618","DOI":"10.1109\/ACCESS.2022.3144079","article-title":"A survey of challenges in spectrum-based software fault localization","volume":"10","author":"Sarhan","year":"2022","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Bekkouche, M. (2024, January 22\u201326). Model checking-enhanced spectrum-based fault localization. Proceedings of the International Conference on Computing Systems and Applications, Sousse, Tunisia.","DOI":"10.1007\/978-3-031-71848-9_28"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Widyasari, R., Prana, G.A.A., Haryono, S.A., Tian, Y., Zachiary, H.N., and Lo, D. (2022, January 16\u201317). XAI4FL: Enhancing spectrum-based fault localization with explainable artificial intelligence. Proceedings of the 30th IEEE\/ACM International Conference on Program Comprehension, Virtual Event.","DOI":"10.1145\/3524610.3527902"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3705305","article-title":"Validity-Preserving Delta Debugging via Generator Trace Reduction","volume":"34","author":"Ren","year":"2025","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, Y., Wang, S., and Wang, Q. (2022, January 16\u201317). Find bugs in static bug finders. Proceedings of the 30th IEEE\/ACM International Conference on Program Comprehension, Virtual Event.","DOI":"10.1145\/3524610.3527899"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Tomassi, D.A., and Rubio-Gonz\u00e1lez, C. (2021, January 15\u201319). On the real-world effectiveness of static bug detectors at finding null pointer exceptions. Proceedings of the 2021 36th IEEE\/ACM International Conference on Automated Software Engineering (ASE), Melbourne, Australia.","DOI":"10.1109\/ASE51524.2021.9678535"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Umann, K., and Porkol\u00e1b, Z. (May, January 27). Towards Better Static Analysis Bug Reports in the Clang Static Analyzer. Proceedings of the 2025 IEEE\/ACM 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), Ottawa, ON, Canada.","DOI":"10.1109\/ICSE-SEIP66354.2025.00021"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Jin, M., Shahriar, S., Tufano, M., Shi, X., Lu, S., Sundaresan, N., and Svyatkovskiy, A. (2023, January 3\u20139). Inferfix: End-to-end program repair with llms. Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, San Francisco, CA, USA.","DOI":"10.1145\/3611643.3613892"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Serebryany, K., Kennelly, C., Phillips, M., Denton, M., Elver, M., Potapenko, A., Morehouse, M., Tsyrklevich, V., Holler, C., and Lettner, J. (2024, January 14\u201320). Gwp-asan: Sampling-based detection of memory-safety bugs in production. Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice, Lisbon, Portugal.","DOI":"10.1145\/3639477.3640328"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Andrianov, P., Mutilin, V., and Gerlits, E. (2025, January 23\u201328). Detecting Data Races in Language Virtual Machines with RaceHunter. Lessons Learned. Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, Trondheim, Norway.","DOI":"10.1145\/3696630.3731435"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Dewan, P., and Gaddis, N. (2024, January 18\u201321). Leveraging Valgrind to Assess Concurrent, Testing-Unaware C Programs. Proceedings of the 2024 IEEE 31st International Conference on High Performance Computing, Data and Analytics Workshop (HiPCW), Bangalore, India.","DOI":"10.1109\/HiPCW63042.2024.00013"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3987981","DOI":"10.1155\/2022\/3987981","article-title":"Sbuglocater: Bug localization based on deep matching and information retrieval","volume":"2022","author":"Huang","year":"2022","journal-title":"Math. Probl. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"114","DOI":"10.3390\/digital4010005","article-title":"Effectiveness of ChatGPT in coding: A comparative analysis of popular large language models","volume":"4","author":"Coello","year":"2024","journal-title":"Digital"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"111961","DOI":"10.1016\/j.jss.2024.111961","article-title":"An empirical assessment of different word embedding and deep learning models for bug assignment","volume":"210","author":"Wang","year":"2024","journal-title":"J. Syst. Softw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1039\/D3DD00219E","article-title":"Retro-BLEU: Quantifying chemical plausibility of retrosynthesis routes through reaction template sequence analysis","volume":"3","author":"Li","year":"2024","journal-title":"Digit. Discov."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"102571","DOI":"10.1016\/j.jocs.2025.102571","article-title":"Assessing the effectiveness of ROUGE as unbiased metric in Extractive vs. Abstractive summarization techniques","volume":"87","author":"Citarella","year":"2025","journal-title":"J. Comput. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1109\/OJCS.2025.3560333","article-title":"A Detailed Comparative Analysis of Automatic Neural Metrics for Machine Translation: BLEURT & BERTScore","volume":"6","author":"Mukherjee","year":"2025","journal-title":"IEEE Open J. Comput. Soc."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4494","DOI":"10.1007\/s00330-023-10493-7","article-title":"How subjective CT image quality assessment becomes surprisingly reliable: Pairwise comparisons instead of Likert scale","volume":"34","author":"Hoeijmakers","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_34","unstructured":"Jia, Q., Cui, J., Xi, R., Liu, C., Rashid, P., Li, R., and Gehringer, E. (2024, January 14\u201317). On assessing the faithfulness of llm-generated feedback on student assignments. Proceedings of the 17th International Conference on Educational Data Mining, Atlanta, Georgia."},{"key":"ref_35","unstructured":"Agarwal, C., Tanneru, S.H., and Lakkaraju, H. (2024). Faithfulness vs. plausibility: On the (un) reliability of explanations from large language models. arXiv."},{"key":"ref_36","unstructured":"Camburu, O.M., Giunchiglia, E., Foerster, J., Lukasiewicz, T., and Blunsom, P. (2019). Can I trust the explainer? Verifying post-hoc explanatory methods. arXiv."},{"key":"ref_37","first-page":"73","article-title":"Utility-Driven Approach to Onboard Scheduling and Execution for an Autonomous Europa Lander Mission","volume":"22","author":"Russino","year":"2025","journal-title":"J. Aerosp. Inf. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Qiu, S., Bicong, E., Huang, X., and Liu, L. (2024, January 8\u201310). Software Defect Prediction Based on Double Traversal AST. Proceedings of the 2024 8th Asian Conference on Artificial Intelligence Technology (ACAIT), Fuzhou, China.","DOI":"10.1109\/ACAIT63902.2024.11022067"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wen, Z., and Fang, Y. (2023, January 23\u201327). Augmenting low-resource text classification with graph-grounded pre-training and prompting. Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, Taipei, Taiwan.","DOI":"10.1145\/3539618.3591641"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/s40745-019-00217-4","article-title":"Improving time complexity and accuracy of the machine learning algorithms through selection of highly weighted top k features from complex datasets","volume":"6","author":"Majeed","year":"2019","journal-title":"Ann. Data Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Wecks, J.O., Voshaar, J., Plate, B.J., and Zimmermann, J. (2024). Generative AI Usage and Exam Performance. arXiv.","DOI":"10.2139\/ssrn.4812513"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Hua, F., Wang, M., Li, G., Peng, B., Liu, C., Zheng, M., Stein, S., Ding, Y., Zhang, E.Z., and Humble, T. (2023, January 12\u201317). Qasmtrans: A qasm quantum transpiler framework for nisq devices. Proceedings of the SC\u201923 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, Denver, CO, USA.","DOI":"10.1145\/3624062.3624222"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s00530-024-01467-w","article-title":"VCounselor: A psychological intervention chat agent based on a knowledge-enhanced large language model","volume":"30","author":"Zhang","year":"2024","journal-title":"Multimed. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"He, G., Demartini, G., and Gadiraju, U. (May, January 26). Plan-then-execute: An empirical study of user trust and team performance when using llm agents as a daily assistant. Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Yokohama Japan.","DOI":"10.1145\/3706598.3713218"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3715108","article-title":"Assessing and analyzing the correctness of github copilot\u2019s code suggestions","volume":"34","author":"Mo","year":"2025","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1007\/s10664-023-10381-0","article-title":"Developers talking about code quality","volume":"28","author":"Bennin","year":"2023","journal-title":"Empir. Softw. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Jo, J., Zhang, H., Cai, J., and Goyal, N. (2025, January 23\u201326). AI Trust Reshaping Administrative Burdens: Understanding Trust-Burden Dynamics in LLM-Assisted Benefits Systems. Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency, Athens, Greece.","DOI":"10.1145\/3715275.3732077"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"4624","DOI":"10.1080\/10447318.2024.2352919","article-title":"When young scholars cooperate with LLMs in academic tasks: The influence of individual differences and task complexities","volume":"41","author":"Wang","year":"2025","journal-title":"Int. J. Hum.\u2013Comput. Interact."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Liu, Y., Sharma, P., Oswal, M., Xia, H., and Huang, Y. (2025, January 5\u20139). PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation. Proceedings of the 2025 ACM Designing Interactive Systems Conference, Madeira, Portugal.","DOI":"10.1145\/3715336.3735789"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1007\/s10664-021-10003-7","article-title":"Where were the repair ingredients for defects4j bugs? exploring the impact of repair ingredient retrieval on the performance of 24 program repair systems","volume":"26","author":"Yang","year":"2021","journal-title":"Empir. Softw. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s10664-023-10291-1","article-title":"Bugs in machine learning-based systems: A faultload benchmark","volume":"28","author":"Morovati","year":"2023","journal-title":"Empir. Softw. Eng."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Wuisang, M.C., Kurniawan, M., Santosa, K.A.W., Gunawan, A.A.S., and Saputra, K.E. (2023, January 16\u201317). An evaluation of the effectiveness of openai\u2019s chatGPT for automated python program bug fixing using quixbugs. Proceedings of the 2023 International Seminar on Application for Technology of Information and Communication (iSemantic), Semarang, Indonesia.","DOI":"10.1109\/iSemantic59612.2023.10295323"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"e1751","DOI":"10.1002\/stvr.1751","article-title":"BUGSJS: A benchmark and taxonomy of JavaScript bugs","volume":"31","author":"Gyimesi","year":"2021","journal-title":"Softw. Test. Verif. Reliab."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Chang, W., Ye, C., and Zhou, H. (2024, January 28\u201331). Fine-Tuning Pre-trained Model with Optimizable Prompt Learning for Code Vulnerability Detection. Proceedings of the 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE), Tsukuba, Japan.","DOI":"10.1109\/ISSRE62328.2024.00021"},{"key":"ref_55","unstructured":"Yang, C., Si, Q., and Lin, Z. (2025). Breaking the Trade-Off Between Faithfulness and Expressiveness for Large Language Models. arXiv."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s10515-025-00549-x","article-title":"Assessing the effectiveness of recent closed-source large language models in fault localization and automated program repair","volume":"33","author":"Wang","year":"2026","journal-title":"Autom. Softw. Eng."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s10515-025-00555-z","article-title":"Investigating the bugs in reinforcement learning programs: Insights from Stack Overflow and GitHub","volume":"33","author":"Song","year":"2026","journal-title":"Autom. Softw. Eng."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1007\/s10515-025-00512-w","article-title":"Context-aware prompting for LLM-based program repair","volume":"32","author":"Li","year":"2025","journal-title":"Autom. Softw. Eng."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3723876","article-title":"Automatically Improving LLM-based Verilog Generation using EDA Tool Feedback","volume":"30","author":"Blocklove","year":"2025","journal-title":"ACM Trans. Des. Autom. Electron. Syst."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.1145\/3763097","article-title":"PReMM: LLM-Based Program Repair for Multi-method Bugs via Divide and Conquer","volume":"9","author":"Xie","year":"2025","journal-title":"Proc. ACM Program. Lang."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1007\/s11219-025-09728-1","article-title":"ReAPR: Automatic program repair via retrieval-augmented large language models","volume":"33","author":"Liu","year":"2025","journal-title":"Softw. Qual. J."},{"key":"ref_62","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s10664-025-10687-1","article-title":"An empirical evaluation of pre-trained large language models for repairing declarative formal specifications","volume":"30","author":"Alhanahnah","year":"2025","journal-title":"Empir. Softw. Eng."},{"key":"ref_63","first-page":"2040","article-title":"Survey of Large-Language-Model-Based Automated Program Repair","volume":"62","author":"Xu","year":"2025","journal-title":"Jisuanji Yanjiu Yu Fazhan\/Comput. Res. Dev."},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"101348","DOI":"10.1016\/j.cola.2025.101348","article-title":"TestLoter: A logic-driven framework for automated unit test generation and error repair using large language models","volume":"84","author":"Yang","year":"2025","journal-title":"J. Comput. Lang."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"1616","DOI":"10.1145\/3729315","article-title":"Scalable, Validated Code Translation of Entire Projects using Large Language Models","volume":"9","author":"Zhang","year":"2025","journal-title":"Proc. ACM Program. Lang."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1145\/3720419","article-title":"UTFix: Change Aware Unit Test Repairing using LLM","volume":"9","author":"Rahman","year":"2025","journal-title":"Proc. ACM Program. Lang."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1007\/s11227-025-07102-3","article-title":"DALO-APR: LLM-based automatic program repair with data augmentation and loss function optimization","volume":"81","author":"Wang","year":"2025","journal-title":"J. Supercomput."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"113449","DOI":"10.1109\/ACCESS.2025.3584060","article-title":"A Systematic Literature Review on Large Language Models Applications in Computer Programming Teaching Evaluation Process","volume":"13","author":"Pereira","year":"2025","journal-title":"IEEE Access"},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"468","DOI":"10.1145\/3689728","article-title":"Statically Contextualizing Large Language Models with Typed Holes","volume":"8","author":"Blinn","year":"2024","journal-title":"Proc. ACM Program. Lang."},{"key":"ref_70","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/TSE.2016.2560811","article-title":"Nopol: Automatic repair of conditional statement bugs in java programs","volume":"43","author":"Xuan","year":"2016","journal-title":"IEEE Trans. Softw. Eng."},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Ros\u00e0, A., Basso, M., Bohnhoff, L., and Binder, W. (2023, January 4\u20137). Automated Runtime Transition between Virtual and Platform Threads in the Java Virtual Machine. Proceedings of the 2023 30th Asia-Pacific Software Engineering Conference (APSEC), Seoul, Republic of Korea.","DOI":"10.1109\/APSEC60848.2023.00080"},{"key":"ref_72","doi-asserted-by":"crossref","unstructured":"Guizzo, G., Bazargani, M., Paixao, M., and Drake, J.H. (2017, January 9\u201311). A hyper-heuristic for multi-objective integration and test ordering in google guava. Proceedings of the International Symposium on Search Based Software Engineering, Paderborn, Germany.","DOI":"10.1007\/978-3-319-66299-2_15"},{"key":"ref_73","doi-asserted-by":"crossref","unstructured":"Gajewski, M., and Zabierowski, W. (2019, January 22\u201326). Analysis and comparison of the Spring framework and play framework performance, used to create web applications in Java. Proceedings of the 2019 IEEE XVth International Conference on the Perspective Technologies and Methods in MEMS Design (MEMSTECH), Polyana, Ukraine.","DOI":"10.1109\/MEMSTECH.2019.8817390"},{"key":"ref_74","doi-asserted-by":"crossref","unstructured":"Walter-Tscharf, F.F.W.V. (2022). Indexing, clustering, and search engine for documents utilizing Elasticsearch and Kibana. Mobile Computing and Sustainable Informatics: Proceedings of ICMCSI 2022, Springer.","DOI":"10.1007\/978-981-19-2069-1_62"},{"key":"ref_75","doi-asserted-by":"crossref","unstructured":"Alqaradaghi, M., Nazir, M.Z.I., and Kozsik, T. (2023). Design and Implement an Accurate Automated Static Analysis Checker to Detect Insecure Use of SecurityManager. Computers, 12.","DOI":"10.3390\/computers12120247"},{"key":"ref_76","doi-asserted-by":"crossref","first-page":"107109","DOI":"10.1016\/j.infsof.2022.107109","article-title":"WINE: Warning miner for improving bug finders","volume":"155","author":"Choi","year":"2023","journal-title":"Inf. Softw. Technol."},{"key":"ref_77","doi-asserted-by":"crossref","first-page":"102212","DOI":"10.1016\/j.mex.2023.102212","article-title":"Gwet\u2019s AC1 is not a substitute for Cohen\u2019s kappa\u2013A comparison of basic properties","volume":"10","author":"Vach","year":"2023","journal-title":"MethodsX"},{"key":"ref_78","doi-asserted-by":"crossref","unstructured":"Cho, D., Lee, H., and Kang, S. (2021). An empirical study of Korean sentence representation with various tokenizations. Electronics, 10.","DOI":"10.3390\/electronics10070845"},{"key":"ref_79","doi-asserted-by":"crossref","first-page":"9203","DOI":"10.1007\/s00521-024-09551-y","article-title":"Automatic detection of code smells using metrics and CodeT5 embeddings: A case study in C#","volume":"36","author":"Slivka","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_80","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/4235.996017","article-title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","volume":"6","author":"Deb","year":"2002","journal-title":"IEEE Trans. Evol. Comput."},{"key":"ref_81","doi-asserted-by":"crossref","unstructured":"Deb, K. (2015). Multi-objective evolutionary algorithms. Springer Handbook of Computational Intelligence, Springer.","DOI":"10.1007\/978-3-662-43505-2_49"},{"key":"ref_82","doi-asserted-by":"crossref","first-page":"100759","DOI":"10.1016\/j.swevo.2020.100759","article-title":"Adaptive simulated binary crossover for rotated multi-objective optimization","volume":"60","author":"Pan","year":"2021","journal-title":"Swarm Evol. Comput."},{"key":"ref_83","unstructured":"Shahedi, K., Gyambrah, N., Li, H., Lamothe, M., and Khomh, F. (2025). An Empirical Study on Method-Level Performance Evolution in Open-Source Java Projects. arXiv."},{"key":"ref_84","first-page":"100101","article-title":"Evaluating explainability in language classification models: A unified framework incorporating feature attribution methods and key factors affecting faithfulness","volume":"9","author":"Dehdarirad","year":"2025","journal-title":"Data Inf. Manag."},{"key":"ref_85","first-page":"1","article-title":"Explainability for large language models: A survey","volume":"15","author":"Zhao","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_86","doi-asserted-by":"crossref","unstructured":"Kern, M., Erata, F., Iser, M., Sinz, C., Loiret, F., Otten, S., and Sax, E. (2019, January 15\u201319). Integrating static code analysis toolchains. Proceedings of the 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC), Milwaukee, WI, USA.","DOI":"10.1109\/COMPSAC.2019.00080"},{"key":"ref_87","first-page":"154","article-title":"A privacy-preserving AI model for autonomous detection and masking of sensitive user data in contact center analytics","volume":"203","author":"Gbenle","year":"2025","journal-title":"World Sci. News"},{"key":"ref_88","doi-asserted-by":"crossref","first-page":"2828","DOI":"10.1145\/3729395","article-title":"DyLin: A Dynamic Linter for Python","volume":"2","author":"Eghbali","year":"2025","journal-title":"Proc. ACM Softw. Eng."},{"key":"ref_89","doi-asserted-by":"crossref","unstructured":"Al-Khafaji, N.J., and Majeed, B.K. (2024, January 6\u20137). Evaluating Large Language Models using Arabic Prompts to Generate Python Codes. Proceedings of the 2024 4th International Conference on Emerging Smart Technologies and Applications (eSmarTA), Sana\u2019a, Yemen.","DOI":"10.1109\/eSmarTA62850.2024.10638877"},{"key":"ref_90","doi-asserted-by":"crossref","unstructured":"Rak-Amnouykit, I., McCrevan, D., Milanova, A., Hirzel, M., and Dolby, J. (2020, January 17). Python 3 types in the wild: A tale of two type systems. Proceedings of the 16th ACM SIGPLAN International Symposium on Dynamic Languages, Virtual.","DOI":"10.1145\/3426422.3426981"},{"key":"ref_91","doi-asserted-by":"crossref","unstructured":"Strong, E., Kleynhans, B., and Kadio\u011flu, S. (2019, January 4\u20136). Mabwiser: A parallelizable contextual multi-armed bandit library for python. Proceedings of the 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), Portland, OR, USA.","DOI":"10.1109\/ICTAI.2019.00129"},{"key":"ref_92","doi-asserted-by":"crossref","first-page":"23556","DOI":"10.1109\/ACCESS.2025.3538108","article-title":"Exploring the Landscape of Programming Language Identification with Machine Learning Approaches","volume":"13","author":"Verma","year":"2025","journal-title":"IEEE Access"},{"key":"ref_93","doi-asserted-by":"crossref","first-page":"5154","DOI":"10.1109\/TSE.2023.3329667","article-title":"Mitigating false positive static analysis warnings: Progress, challenges, and opportunities","volume":"49","author":"Guo","year":"2023","journal-title":"IEEE Trans. Softw. Eng."},{"key":"ref_94","first-page":"59304","article-title":"To repeat or not to repeat: Insights from scaling llm under token-crisis","volume":"36","author":"Xue","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_95","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1007\/s42979-025-03794-9","article-title":"Robust Multi-Dialect End-to-End ASR Model Jointly with Beam Search Threshold Pruning and LLM","volume":"6","author":"Priya","year":"2025","journal-title":"SN Comput. Sci."},{"key":"ref_96","doi-asserted-by":"crossref","unstructured":"Guo, L., Wang, Y., Shi, E., Zhong, W., Zhang, H., Chen, J., Zhang, R., Ma, Y., and Zheng, Z. (2024, January 16\u201320). When to stop? towards efficient code generation in llms with excess token prevention. Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, Vienna, Austria.","DOI":"10.1145\/3650212.3680343"},{"key":"ref_97","first-page":"10","article-title":"Hallucinations in large language models and their influence on legal reasoning: Examining the risks of ai-generated factual inaccuracies in judicial processes","volume":"10","author":"Latif","year":"2025","journal-title":"J. Comput. Intell. Mach. Reason. Decis.-Mak."},{"key":"ref_98","doi-asserted-by":"crossref","first-page":"100076","DOI":"10.1016\/j.jrt.2024.100076","article-title":"C-XAI: A conceptual framework for designing XAI tools that support trust calibration","volume":"17","author":"Naiseh","year":"2024","journal-title":"J. Responsible Technol."},{"key":"ref_99","doi-asserted-by":"crossref","unstructured":"Li, K., Liu, H., Zhang, L., and Chen, Y. (2024, January 10\u201311). Automatic Inspection of Static Application Security Testing (SAST) Reports via Large Language Model Reasoning. Proceedings of the International Conference on AI Logic and Applications, Lanzhou, China.","DOI":"10.1007\/978-981-96-0354-1_11"},{"key":"ref_100","doi-asserted-by":"crossref","first-page":"6216","DOI":"10.1109\/TKDE.2025.3599265","article-title":"TokenRec: Learning to Tokenize ID for LLM-Based Generative Recommendations","volume":"37","author":"Qu","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/534\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T13:48:19Z","timestamp":1764942499000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/14\/12\/534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,5]]},"references-count":100,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["computers14120534"],"URL":"https:\/\/doi.org\/10.3390\/computers14120534","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,5]]}}}