{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T15:54:05Z","timestamp":1782143645206,"version":"3.54.5"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,2]]},"DOI":"10.1109\/csr61664.2024.10679494","type":"proceedings-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:21:51Z","timestamp":1727198511000},"page":"296-302","source":"Crossref","is-referenced-by-count":52,"title":["CyberMetric: A Benchmark Dataset based on Retrieval-Augmented Generation for Evaluating LLMs in Cybersecurity Knowledge"],"prefix":"10.1109","author":[{"given":"Norbert","family":"Tihanyi","sequence":"first","affiliation":[{"name":"Technology Innovation Institute (TII),Abu Dhabi,United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed Amine","family":"Ferrag","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute (TII),Abu Dhabi,United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ridhi","family":"Jain","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute (TII),Abu Dhabi,United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamas","family":"Bisztray","sequence":"additional","affiliation":[{"name":"University of Oslo,Oslo,Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Merouane","family":"Debbah","sequence":"additional","affiliation":[{"name":"Khalifa University,Abu Dhabi,United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref2","article-title":"A new era in software security: Towards self-healing software via large language models and formal verification","author":"Charalambous","year":"2023","journal-title":"arXiv"},{"key":"ref3","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature.2016.19575"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.540"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1434770.1434772"},{"key":"ref7","article-title":"SecureFalcon: The Next Cyber Reasoning System for Cyber Security","author":"Ferrag","year":"2023","journal-title":"arXiv"},{"key":"ref8","article-title":"Revolutionizing Cyber Threat Detection with Large Language Models","author":"Ferrag","year":"2023","journal-title":"arXiv"},{"key":"ref9","article-title":"Codeapex: A bilingual programming evaluation benchmark for large language models","author":"Fu","year":"2023","journal-title":"arXiv"},{"key":"ref10","article-title":"Dureader: a chinese machine reading comprehension dataset from real-world applications","author":"He","year":"2017","journal-title":"arXiv"},{"key":"ref11","article-title":"Measuring mathematical problem solving with the math dataset","author":"Hendrycks","journal-title":"NeurIPS, 2021"},{"key":"ref12","article-title":"Large language models for software engineering: A systematic literature review","author":"Hou","year":"2023","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1515\/9780691235141"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6319"},{"key":"ref15","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","article-title":"SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security","volume-title":"arXiv","author":"Liu","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4825426"},{"key":"ref19","volume-title":"Fine-tune a transformer model for grammar correction","year":"2021"},{"key":"ref20","article-title":"Drcd: A chinese machine reading comprehension dataset","author":"Shao","year":"2018","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"ref23","article-title":"BloombergGPT: A Large Language Model for Finance","author":"Wu","year":"2023","journal-title":"arXiv"},{"key":"ref24","article-title":"When llms meet cybersecurity: A systematic literature review","author":"Zhang","year":"2024","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.246"}],"event":{"name":"2024 IEEE International Conference on Cyber Security and Resilience (CSR)","location":"London, United Kingdom","start":{"date-parts":[[2024,9,2]]},"end":{"date-parts":[[2024,9,4]]}},"container-title":["2024 IEEE International Conference on Cyber Security and Resilience (CSR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10679369\/10679342\/10679494.pdf?arnumber=10679494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T05:22:41Z","timestamp":1727241761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10679494\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/csr61664.2024.10679494","relation":{},"subject":[],"published":{"date-parts":[[2024,9,2]]}}}