{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T01:59:09Z","timestamp":1781143149964,"version":"3.54.1"},"reference-count":95,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100019258","name":"Vingroup JSC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100019258","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018311","name":"VNU ARC","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Systems and Software"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.jss.2026.112852","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T16:58:11Z","timestamp":1773334691000},"page":"112852","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Model-agnostic quality assessment for LLM-generated code via dynamic internal representation selection"],"prefix":"10.1016","volume":"237","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3377-6565","authenticated-orcid":false,"given":"Thanh","family":"Trong Vu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7318-6896","authenticated-orcid":false,"given":"Tuan-Dung","family":"Bui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3596-2352","authenticated-orcid":false,"given":"Thu-Trang","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8970-9870","authenticated-orcid":false,"given":"Son","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9407-1971","authenticated-orcid":false,"given":"Hieu","family":"Dinh Vo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jss.2026.112852_bib0001","series-title":"International Conference on Software Engineering and Computer Systems","first-page":"46","article-title":"Software quality models: a comparative study","author":"Al-Badareen","year":"2011"},{"key":"10.1016\/j.jss.2026.112852_bib0002","unstructured":"Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al., 2023. Palm 2 technical report.arXiv: 2305.10403."},{"issue":"8","key":"10.1016\/j.jss.2026.112852_bib0003","doi-asserted-by":"crossref","first-page":"852","DOI":"10.1038\/s42256-024-00881-z","article-title":"Factuality challenges in the era of large language models and opportunities for fact-checking","volume":"6","author":"Augenstein","year":"2024","journal-title":"Nature Mach. Intell."},{"key":"10.1016\/j.jss.2026.112852_bib0004","unstructured":"Austin, J., Odena, A., Nye, M., Bosma, M., Michalewski, H., Dohan, D., Jiang, E., Cai, C., Terry, M., Le, Q., et al., 2021. Program synthesis with large language models.arXiv: 2108.07732."},{"key":"10.1016\/j.jss.2026.112852_bib0005","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"967","article-title":"The internal state of an LLM knows when it\u2019s lying","author":"Azaria","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0006","unstructured":"Bandit. https:\/\/bandit.readthedocs.io\/en\/latest\/."},{"key":"10.1016\/j.jss.2026.112852_bib0007","unstructured":"Bui, T.-D., Luu-Van, D.-T., Nguyen, T.-P., Nguyen, T.-T., Nguyen, S., Vo, H. D., 2024a. Rambo: enhancing rag-based repository-level method body completion.arXiv: 2409.15204."},{"key":"10.1016\/j.jss.2026.112852_bib0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.jss.2025.112570","article-title":"Correctness assessment of code generated by large language models using internal representations","volume":"230","author":"Bui","year":"2025","journal-title":"J. Syst. Softw."},{"key":"10.1016\/j.jss.2026.112852_bib0009","unstructured":"Codegeex2. https:\/\/github.com\/zai-org\/CodeGeeX2."},{"key":"10.1016\/j.jss.2026.112852_bib0010","unstructured":"CodeQL. https:\/\/codeql.github.com."},{"key":"10.1016\/j.jss.2026.112852_bib0011","unstructured":"Chen, C., Liu, K., Chen, Z., Gu, Y., Wu, Y., Tao, M., Fu, Z., Ye, J., 2024a. Inside: Llms\u2019 internal states retain the power of hallucination detection.arXiv: 2305.10403."},{"key":"10.1016\/j.jss.2026.112852_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12954","article-title":"Vitamin: designing scalable vision models in the vision-language era","author":"Chen","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0013","unstructured":"Chen, M., Tworek, J., Jun, H., Yuan, Q., de Oliveira, P. H. P., Kaplan, J., Edwards, H., Burda, Y., Joseph, N., Brockman, G., et al., 2021. Evaluating large language models trained on code.arXiv: 2107.03374."},{"key":"10.1016\/j.jss.2026.112852_bib0014","series-title":"Companion Proceedings of the 32nd ACM International Conference on the Foundations of Software Engineering","first-page":"572","article-title":"Chatunitest: a framework for llm-based test generation","author":"Chen","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0015","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"1419","article-title":"Lookback lens: detecting and mitigating contextual hallucinations in large language models using only attention maps","author":"Chuang","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0016","series-title":"Proceedings of the 15th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)","first-page":"1","article-title":"An empirical study of rule-based and learning-based approaches for static application security testing","author":"Croft","year":"2021"},{"key":"10.1016\/j.jss.2026.112852_bib0017","unstructured":"Dai, S.-C., Xu, J., Tao, G., 2025. A comprehensive study of llm secure code generation.2503.15554."},{"key":"10.1016\/j.jss.2026.112852_bib0018","unstructured":"DeepSeek, 2023. Deepseek coder: let the code write itself. https:\/\/github.com\/deepseek-ai\/DeepSeek-Coder."},{"key":"10.1016\/j.jss.2026.112852_bib0019","series-title":"2022 IEEE International Conference on Software Analysis, Evolution and Reengineering","first-page":"959","article-title":"Velvet: a novel ensemble learning approach to automatically locate vulnerable statements","author":"Ding","year":"2022"},{"issue":"3","key":"10.1016\/j.jss.2026.112852_bib0020","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10664-022-10118-5","article-title":"Can pre-trained code embeddings improve model performance? revisiting the use of code embeddings in software engineering tasks","volume":"27","author":"Ding","year":"2022","journal-title":"Empir. Softw. Eng."},{"issue":"8017","key":"10.1016\/j.jss.2026.112852_bib0021","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","article-title":"Detecting hallucinations in large language models using semantic entropy","volume":"630","author":"Farquhar","year":"2024","journal-title":"Nature"},{"key":"10.1016\/j.jss.2026.112852_bib0022","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2020","first-page":"1536","article-title":"CodeBERT: a pre-trained model for programming and natural languages","author":"Feng","year":"2020"},{"key":"10.1016\/j.jss.2026.112852_bib0023","unstructured":"Ferrando, J., Sarti, G., Bisazza, A., Costa-juss\u00e0, M. R., 2024. A primer on the inner workings of transformer-based language models.arXiv: 2405.00208."},{"issue":"4","key":"10.1016\/j.jss.2026.112852_bib0024","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","article-title":"Gpt-3: its nature, scope, limits, and consequences","volume":"30","author":"Floridi","year":"2020","journal-title":"Minds Mach."},{"key":"10.1016\/j.jss.2026.112852_bib0025","series-title":"2022 IEEE\/ACM 19th International Conference on Mining Software Repositories (MSR)","first-page":"608","article-title":"Linevul: a transformer-based line-level vulnerability prediction","author":"Fu","year":"2022"},{"key":"10.1016\/j.jss.2026.112852_bib0026","unstructured":"Fu, Y., Baker, E., Ding, Y., Chen, Y., 2024. Constrained decoding for secure code generation.arXiv: 2405.00218."},{"key":"10.1016\/j.jss.2026.112852_bib0027","unstructured":"Fu, Y., Liang, P., Tahir, A., Li, Z., Shahin, M., Yu, J., Chen, J., 2023. Security weaknesses of copilot generated code in github.arXiv: 2310.02059."},{"key":"10.1016\/j.jss.2026.112852_bib0028","unstructured":"Github copilot. https:\/\/github.com\/features\/copilot."},{"key":"10.1016\/j.jss.2026.112852_bib0029","series-title":"Findings of the Association for Computational Linguistics ACL 2024","first-page":"10218","article-title":"Llm factoscope: uncovering llms\u2019 factual discernment through measuring inner states","author":"He","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0030","series-title":"IEEE\/ACM 19th International Conference on Mining Software Repositories, MSR 2022, Pittsburgh, PA, USA, May 23-24, 2022","first-page":"596","article-title":"LineVD: statement-level vulnerability detection using graph neural networks","author":"Hin","year":"2022"},{"key":"10.1016\/j.jss.2026.112852_bib0031","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"6953","article-title":"Knowledge-centric hallucination detection","author":"Hu","year":"2024"},{"issue":"2","key":"10.1016\/j.jss.2026.112852_bib0032","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3703155","article-title":"A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions","volume":"43","author":"Huang","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.jss.2026.112852_bib0033","unstructured":"Huang, Y., Song, J., Wang, Z., Zhao, S., Chen, H., Juefei-Xu, F., Ma, L., 2023. Look before you leap: an exploratory study of uncertainty measurement for large language models.arXiv: 2307.10236."},{"key":"10.1016\/j.jss.2026.112852_bib0034","series-title":"2023 IEEE\/ACM 20th International Conference on Mining Software Repositories (MSR)","first-page":"563","article-title":"Large language models and simple, stupid bugs","author":"Jesse","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0035","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1109\/TASLP.2024.3519814","article-title":"Zero-shot prompting for llm-based machine translation using in-domain target sentences","volume":"Vol. 33","author":"Ji","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.jss.2026.112852_bib0036","series-title":"Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP","first-page":"88","article-title":"Llm internal states reveal hallucination risk faced with a query","author":"Ji","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0037","unstructured":"Jiang, J., Zhou, J., Zhu, Z., 2024. Tracing representation progression: analyzing and enhancing layer-wise similarity. arXiv: 2406.14479."},{"key":"10.1016\/j.jss.2026.112852_bib0038","series-title":"Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"1646","article-title":"Inferfix: end-to-end program repair with llms","author":"Jin","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0039","series-title":"Proceedings of the 37th International Conference on Machine Learning","article-title":"Learning and evaluating contextual embedding of source code","author":"Kanade","year":"2020"},{"key":"10.1016\/j.jss.2026.112852_bib0040","series-title":"Proceedings of the 28th International Conference on Evaluation and Assessment in Software Engineering","first-page":"600","article-title":"Llm security guard for code","author":"Kavian","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0041","article-title":"The cost of poor software quality in the US: a 2022 report","author":"Krasner","year":"2022","journal-title":"Consort. Inf. Software Quality (CISQ)"},{"key":"10.1016\/j.jss.2026.112852_bib0042","series-title":"Findings of the Association for Computational Linguistics: ACL 2024","first-page":"3603","article-title":"Deveval: a manually-annotated code generation benchmark aligned with real-world code repositories","author":"Li","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0043","series-title":"Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"292","article-title":"Vulnerability detection with fine-grained interpretations","author":"Li","year":"2021"},{"key":"10.1016\/j.jss.2026.112852_bib0044","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"18608","article-title":"Flexkbqa: a flexible llm-powered framework for few-shot knowledge base question answering","volume":"Vol. 38","author":"Li","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0045","series-title":"Proceedings of the 46th IEEE\/ACM International Conference on Software Engineering","first-page":"1","article-title":"A large-scale survey on the usability of ai programming assistants: successes and challenges","author":"Liang","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0046","unstructured":"Liu, F., Liu, Y., Shi, L., Huang, H., Wang, R., Yang, Z., Zhang, L., Li, Z., Ma, Y., 2024a. Exploring and evaluating hallucinations in llm-powered code generation. arXiv: 2404.00971."},{"key":"10.1016\/j.jss.2026.112852_bib0047","doi-asserted-by":"crossref","first-page":"21558","DOI":"10.52202\/075280-0943","article-title":"Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jss.2026.112852_bib0048","first-page":"21558","article-title":"Is your code generated by chatgpt really correct? rigorous evaluation of large language models for code generation","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"10.1016\/j.jss.2026.112852_bib0049","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1109\/TSE.2024.3392499","article-title":"No need to lift a finger anymore? assessing the quality of code generation by chatgpt","volume":"50","author":"Liu","year":"2024","journal-title":"IEEE Trans. Software Eng."},{"key":"10.1016\/j.jss.2026.112852_bib0050","doi-asserted-by":"crossref","first-page":"1548","DOI":"10.1109\/TSE.2024.3392499","article-title":"No need to lift a finger anymore? assessing the quality of code generation by chatgpt","volume":"Vol. 50","author":"Liu","year":"2024","journal-title":"IEEE Trans. Software Eng."},{"key":"10.1016\/j.jss.2026.112852_bib0051","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"9004","article-title":"SelfcheckGPT: zero-resource black-box hallucination detection for generative large language models","author":"Manakul","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0052","unstructured":"Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., Gao, J., 2024. Large language models: a survey. arXiv: 2402.06196."},{"key":"10.1016\/j.jss.2026.112852_bib0053","unstructured":"Mohsin, A., Janicke, H., Wood, A., Sarker, I. H., Maglaras, L., Janjua, N., 2024. Can we trust large language models generated code? a framework for in-context learning, security patterns, and code evaluations across diverse LLMs. arXiv: 2406.12513."},{"issue":"FSE","key":"10.1016\/j.jss.2026.112852_bib0054","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1145\/3660810","article-title":"Clarifygpt: a framework for enhancing llm-based code generation via requirements clarification","volume":"1","author":"Mu","year":"2024","journal-title":"Proc. ACM Softw. Eng."},{"key":"10.1016\/j.jss.2026.112852_bib0055","doi-asserted-by":"crossref","DOI":"10.1016\/j.infsof.2024.107406","article-title":"Context-based statement-level vulnerability localization","volume":"169","author":"Nguyen","year":"2024","journal-title":"Inf. Softw. Technol."},{"key":"10.1016\/j.jss.2026.112852_bib0056","series-title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22","first-page":"5546","article-title":"Deep learning meets software engineering: a survey on pre-trained models of source code","author":"Niu","year":"2022"},{"key":"10.1016\/j.jss.2026.112852_bib0057","unstructured":"Nunez, A., Islam, N. T., Jha, S. K., Najafirad, P., 2024. Autosafecoder: a multi-agent framework for securing LLM code generation through static analysis and fuzz testing. arXiv: 2409.10737."},{"key":"10.1016\/j.jss.2026.112852_bib0058","unstructured":"OpenAI,. Gpt-oss. https:\/\/github.com\/openai\/gpt-oss."},{"key":"10.1016\/j.jss.2026.112852_bib0059","series-title":"2025 IEEE\/ACM International Workshop on Large Language Models for Code (LLM4Code)","first-page":"33","article-title":"Cweval: outcome-driven evaluation on functionality and security of llm code generation","author":"Peng","year":"2025"},{"key":"10.1016\/j.jss.2026.112852_bib0060","series-title":"Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security","first-page":"2785","article-title":"Do users write more insecure code with ai assistants?","author":"Perry","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0061","unstructured":"Roziere, B., Gehring, J., Gloeckle, F., Sootla, S., Gat, I., Tan, X. E., Adi, Y., Liu, J., Remez, T., Rapin, J., et al., 2023. Code llama: open foundation models for code. arXiv: 2308.12950."},{"key":"10.1016\/j.jss.2026.112852_bib0062","series-title":"32nd USENIX Security Symposium (USENIX Security 23)","first-page":"2205","article-title":"Lost at c: a user study on the security implications of large language model code assistants","author":"Sandoval","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0063","series-title":"Proceedings of the 1st International Workshop on Mining Software Repositories Applications for Privacy and Security","first-page":"29","article-title":"Securityeval dataset: mining vulnerability examples to evaluate machine learning-based code generation techniques","author":"Siddiq","year":"2022"},{"key":"10.1016\/j.jss.2026.112852_bib0064","series-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering Workshops","first-page":"54","article-title":"Sallm: security assessment of generated code","author":"Siddiq","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0065","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2721","article-title":"On early detection of hallucinations in factual question answering","author":"Snyder","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0066","series-title":"7th Annual Symposium on Machine Programming","article-title":"An empirical study of code generation errors made by large language models","author":"Song","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0067","unstructured":"Spiess, C., Gros, D., Pai, K. S., Pradel, M., Rabin, M. R. I., Alipour, A., Jha, S., Devanbu, P., Ahmed, T., 2024. Calibration and correctness of language models for code. arXiv: 2402.02047."},{"key":"10.1016\/j.jss.2026.112852_bib0068","first-page":"34188","article-title":"Llm-check: investigating detection of hallucinations in large language models","volume":"37","author":"Sriramanan","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jss.2026.112852_bib0069","series-title":"2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE)","first-page":"419","article-title":"Source code summarization in the era of large language models","author":"Sun","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0070","doi-asserted-by":"crossref","unstructured":"Tambon, F., Dakhel, A. M., Nikanjam, A., Khomh, F., Desmarais, M. C., Antoniol, G., 2024. Bugs in large language models generated code. arXiv: 2403.08937.","DOI":"10.1007\/s10664-025-10614-4"},{"key":"10.1016\/j.jss.2026.112852_bib0071","unstructured":"C. Team, Zhao, H., Hui, J., Howland, J., Nguyen, N., Zuo, S., Hu, A., Choquette-Choo, C. A., Shen, J., Kelley, J., et al., 2024. Codegemma: open code models based on gemma. arXiv: 2406.11409."},{"issue":"2","key":"10.1016\/j.jss.2026.112852_bib0072","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s10664-024-10590-1","article-title":"How secure is AI-generated code: a large-scale comparison of large language models","volume":"30","author":"Tihanyi","year":"2025","journal-title":"Empir. Softw. Eng."},{"key":"10.1016\/j.jss.2026.112852_bib0073","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., et al., 2023. Llama: open and efficient foundation language models. arXiv: 2302.13971."},{"key":"10.1016\/j.jss.2026.112852_bib0074","series-title":"Chi Conference on Human Factors in Computing Systems Extended Abstracts","first-page":"1","article-title":"Expectation vs. experience: evaluating the usability of code generation tools powered by large language models","author":"Vaithilingam","year":"2022"},{"key":"10.1016\/j.jss.2026.112852_bib0075","unstructured":"Vu, T. T., Bui, T.-D., Nguyen, T.-T., Nguyen, S., Vo, D. H.,. Model-agnostic quality assessment for LLM-generated code via dynamic internal representation selection. https:\/\/github.com\/iSE-UET-VNU\/AUTOPROBE."},{"issue":"ISSTA","key":"10.1016\/j.jss.2026.112852_bib0076","doi-asserted-by":"crossref","first-page":"1955","DOI":"10.1145\/3728963","article-title":"Can llms replace human evaluators? an empirical study of llm-as-a-judge in software engineering","volume":"2","author":"Wang","year":"2025","journal-title":"Proc. ACM on Softw. Eng."},{"key":"10.1016\/j.jss.2026.112852_bib0077","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"8696","article-title":"Codet5: identifier-aware unified pre-trained encoder-decoder models for code understanding and generation","author":"Wang","year":"2021"},{"key":"10.1016\/j.jss.2026.112852_bib0078","series-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering","first-page":"1258","article-title":"Hits: high-coverage llm-based unit test generation via method slicing","author":"Wang","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0079","series-title":"2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE)","article-title":"Towards understanding the characteristics of code generation errors made by large language models","author":"Wang","year":"2025"},{"key":"10.1016\/j.jss.2026.112852_bib0080","series-title":"2023 IEEE International Conference on Big Data (BigData)","first-page":"2786","article-title":"Empirical study of llm fine-tuning for text classification in legal document review","author":"Wei","year":"2023"},{"key":"10.1016\/j.jss.2026.112852_bib0081","unstructured":"Wei, Y., Wang, Z., Liu, J., Ding, Y., Zhang, L., 2023b. Magicoder: source code is all you need. arXiv: 2312.02120."},{"key":"10.1016\/j.jss.2026.112852_bib0082","series-title":"Proceedings of the 41st International Conference on Machine Learning","first-page":"57069","article-title":"Characterizing truthfulness in large language model generations with local intrinsic dimension","author":"Yin","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0083","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","first-page":"2471","article-title":"Repocoder: repository-level code completion through iterative retrieval and generation","author":"Zhang","year":"2023"},{"issue":"11","key":"10.1016\/j.jss.2026.112852_bib0084","first-page":"1","article-title":"A systematic survey of text summarization: from statistical methods to large language models","volume":"57","author":"Zhang","year":"2025","journal-title":"ACM Comput. Surv."},{"issue":"8","key":"10.1016\/j.jss.2026.112852_bib0085","doi-asserted-by":"crossref","first-page":"5625","DOI":"10.1109\/TPAMI.2024.3369699","article-title":"Vision-language models for vision tasks: a survey","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jss.2026.112852_bib0086","unstructured":"Zhang, J., Xu, C., Gai, Y., Lecue, F., Song, D., Li, B., 2024b. Knowhalu: hallucination detection via multi-form knowledge based factual checking. arXiv: 2404.02935."},{"key":"10.1016\/j.jss.2026.112852_bib0087","unstructured":"Zhang, J., Zhang, H., Xia, C., Sun, L., 2020. Graph-bert: only attention is needed for learning graph representations. arXiv: 2305.10403."},{"key":"10.1016\/j.jss.2026.112852_bib0088","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1946","article-title":"Self-alignment for factuality: mitigating hallucinations in LLMs via self-evaluation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.jss.2026.112852_bib0089","series-title":"Proceedings of the ACM on Web Conference 2025","first-page":"2032","article-title":"Teleclass: taxonomy enrichment and llm-enhanced hierarchical text classification with minimal supervision","author":"Zhang","year":"2025"},{"key":"10.1016\/j.jss.2026.112852_bib0090","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hu, X., Zhang, H., Zhang, J., Wan, X., 2025c. Icr probe: tracking hidden state dynamics for reliable hallucination detection in llms. arXiv: 2507.16488.","DOI":"10.18653\/v1\/2025.acl-long.880"},{"issue":"ISSTA","key":"10.1016\/j.jss.2026.112852_bib0091","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1145\/3728894","article-title":"Llm hallucinations in practical code generation: phenomena, mechanism, and mitigation","volume":"2","author":"Zhang","year":"2025","journal-title":"Proceedings of the ACM on Software Engineering"},{"key":"10.1016\/j.jss.2026.112852_bib0092","first-page":"130408","article-title":"Probing the decision boundaries of in-context learning in large language models","volume":"37","author":"Zhao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jss.2026.112852_bib0093","series-title":"Proceedings of the 39th IEEE\/ACM International Conference on Automated Software Engineering","first-page":"1732","article-title":"Coding-PTMs: how to find optimal code pre-trained models for code embedding in vulnerability detection?","author":"Zhao","year":"2024"},{"issue":"2","key":"10.1016\/j.jss.2026.112852_bib0094","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1007\/s10664-024-10602-0","article-title":"Towards an understanding of large language models in software engineering tasks","volume":"30","author":"Zheng","year":"2025","journal-title":"Emp. Softw. Eng."},{"key":"10.1016\/j.jss.2026.112852_bib0095","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","first-page":"1393","article-title":"Detecting hallucinated content in conditional neural sequence generation","author":"Zhou","year":"2021"}],"container-title":["Journal of Systems and Software"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0164121226000865?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0164121226000865?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T01:12:51Z","timestamp":1781140371000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0164121226000865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":95,"alternative-id":["S0164121226000865"],"URL":"https:\/\/doi.org\/10.1016\/j.jss.2026.112852","relation":{},"ISSN":["0164-1212"],"issn-type":[{"value":"0164-1212","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Model-agnostic quality assessment for LLM-generated code via dynamic internal representation selection","name":"articletitle","label":"Article Title"},{"value":"Journal of Systems and Software","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jss.2026.112852","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112852"}}