{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T03:52:45Z","timestamp":1785901965782,"version":"3.56.0"},"reference-count":40,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["MUR IR0000008"],"award-info":[{"award-number":["MUR IR0000008"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002347","name":"BMBF Bonn","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cell.com","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Patterns"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.patter.2026.101569","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:34:28Z","timestamp":1780670068000},"page":"101569","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"title":["SelfCheck-Eval: A multi-module framework for zero-resource hallucination detection in large language models"],"prefix":"10.1016","volume":"7","author":[{"given":"Diyana","family":"Muhammed","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giusy Giulia","family":"Tuccari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1212-0101","authenticated-orcid":false,"given":"Gollam","family":"Rabby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S\u00f6ren","family":"Auer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahar","family":"Vahdati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patter.2026.101569_bib1","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","first-page":"8299","article-title":"Beyond the limits: A survey of techniques to extend the context length in large language models","author":"Wang","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib2","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023","first-page":"9004","article-title":"Selfcheckgpt: Zero-resource black-box hallucination detection for generative large language models","author":"Potsawee","year":"2023"},{"key":"10.1016\/j.patter.2026.101569_bib3","doi-asserted-by":"crossref","unstructured":"Alnuhait D., Kirtane N., Khalifa M., Peng H. Factcheckmate: Preemptively detecting and mitigating hallucinations in LMs. Findings of the Association for Computational Linguistics: EMNLP 2025; 2025. p. 12413\u201312428. https:\/\/aclanthology.org\/2025.findings-emnlp.663.","DOI":"10.18653\/v1\/2025.findings-emnlp.663"},{"key":"10.1016\/j.patter.2026.101569_bib4","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"4542","article-title":"Reference-free hallucination detection for large vision-language models","author":"Li","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib5","article-title":"The hallucinations leaderboard - an open effort to measure hallucinations in large language models","author":"Hong","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib6","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2022, Dublin, Ireland, May 22-27, 2022","first-page":"3214","article-title":"Truthfulqa: Measuring how models mimic human falsehoods","author":"Lin","year":"2022"},{"key":"10.1016\/j.patter.2026.101569_bib7","series-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP 2023, Singapore, December 6-10, 2023","first-page":"6449","article-title":"Halueval: A large-scale hallucination evaluation benchmark for large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patter.2026.101569_bib8","series-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"6723","article-title":"A token-level reference-free hallucination detection benchmark for free-form text generation","author":"Liu","year":"2022"},{"key":"10.1016\/j.patter.2026.101569_bib9","series-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI 2024)","first-page":"6216","article-title":"Factchd: Benchmarking fact-conflicting hallucination detection","author":"Chen","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib10","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023","first-page":"12370","article-title":"Wikibio: a semantic resource for the intersectional analysis of biographical events","author":"Stranisci","year":"2023"},{"key":"10.1016\/j.patter.2026.101569_bib11","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024, Miami, FL, USA, November 12-16, 2024","first-page":"3753","article-title":"Incubating text classifiers following user instruction with nothing but LLM","author":"Peng","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib12","series-title":"Proceedings of the ACM Web Conference 2023","first-page":"1662","article-title":"\u201cwhy is this misleading?\u201d: Detecting news headline hallucinations with explanations","author":"Shen","year":"2023"},{"key":"10.1016\/j.patter.2026.101569_bib13","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2021, Online, June 6-11, 2021","first-page":"4812","article-title":"Understanding factuality in abstractive summarization with FRANK: A benchmark for factuality metrics","author":"Pagnoni","year":"2021"},{"key":"10.1016\/j.patter.2026.101569_bib14","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","first-page":"684","article-title":"Diving deep into modes of fact hallucinations in dialogue systems","author":"Das","year":"2022"},{"key":"10.1016\/j.patter.2026.101569_bib15","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"9802","article-title":"When not to trust language models: Investigating effectiveness of parametric and non-parametric memories","author":"Mallen","year":"2023"},{"key":"10.1016\/j.patter.2026.101569_bib16","article-title":"Mc-nest\u2013enhancing mathematical reasoning in large language models with a monte carlo nash equilibrium self-refine tree","author":"Rabby","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib17","first-page":"809","article-title":"FEVER: a large-scale dataset for fact extraction and verification","volume":"1","author":"Thorne","year":"2018"},{"key":"10.1016\/j.patter.2026.101569_bib18","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics","first-page":"1946","article-title":"Self-alignment for factuality: Mitigating hallucinations in llms via self-evaluation","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib19","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib20","article-title":"Measuring mathematical problem solving with the MATH dataset","author":"Hendrycks","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks"},{"key":"10.1016\/j.patter.2026.101569_bib21","series-title":"EMNLP","first-page":"4247","article-title":"Fg-prm: Fine-grained hallucination detection and mitigation in language model mathematical reasoning. Findings of the Association for Computational Linguistics","author":"Li","year":"2025"},{"key":"10.1016\/j.patter.2026.101569_bib22","series-title":"International Conference on Learning Representations (ICLR)","first-page":"39578","article-title":"Let\u2019s verify step by step","author":"Lightman","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib23","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.patter.2026.101569_bib24","series-title":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","first-page":"2080","article-title":"Are NLP models really able to solve simple math word problems?","author":"Patel","year":"2021"},{"key":"10.1016\/j.patter.2026.101569_bib25","series-title":"1st International Conference on Learning Representations, ICLR 2013, Scottsdale, Arizona, USA, May 2-4, 2013, Workshop Track Proceedings","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013"},{"key":"10.1016\/j.patter.2026.101569_bib26","first-page":"1112","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","volume":"1","author":"Williams","year":"2018"},{"key":"10.1016\/j.patter.2026.101569_bib27","series-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023)","article-title":"Efficient finetuning of quantized llms","author":"Dettmers","year":"2023"},{"key":"10.1016\/j.patter.2026.101569_bib28","article-title":"GPT-4 technical report","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib29","article-title":"A comprehensive capability analysis of GPT-3 and GPT-3.5 series models","author":"Ye","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib30","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib31","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib32","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib33","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib34","article-title":"Roberta: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib35","doi-asserted-by":"crossref","first-page":"2947","DOI":"10.1109\/TASLP.2023.3293046","article-title":"Logiqa 2.0\u2014an improved dataset for logical reasoning in natural language understanding","volume":"31","author":"Liu","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.patter.2026.101569_bib36","article-title":"Evaluating robustness of reward models for mathematical reasoning","author":"Kim","year":"2024","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib37","series-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers","first-page":"9426","article-title":"Math-shepherd: Verify and reinforce LLMs step-by-step without human annotations","author":"Wang","year":"2024"},{"key":"10.1016\/j.patter.2026.101569_bib38","article-title":"Fine-tuning language models from human preferences","author":"Ziegler","year":"2019","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib39","article-title":"Solving math word problems with process- and outcome-based feedback","author":"Uesato","year":"2022","journal-title":"arXiv"},{"key":"10.1016\/j.patter.2026.101569_bib40","unstructured":"Muhammed, D., Tuccari, G. G., Rabby, G., Auer, S., and Vahdati, S. Selfcheck-eval (2026). https:\/\/doi.org\/10.5281\/zenodo.19431204."}],"container-title":["Patterns"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666389926000784?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2666389926000784?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T03:24:18Z","timestamp":1785900258000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2666389926000784"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["S2666389926000784"],"URL":"https:\/\/doi.org\/10.1016\/j.patter.2026.101569","relation":{},"ISSN":["2666-3899"],"issn-type":[{"value":"2666-3899","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SelfCheck-Eval: A multi-module framework for zero-resource hallucination detection in large language models","name":"articletitle","label":"Article Title"},{"value":"Patterns","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patter.2026.101569","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"101569"}}