{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:28:53Z","timestamp":1783790933084,"version":"3.55.0"},"reference-count":46,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T00:00:00Z","timestamp":1761609600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Large Language Models (LLMs) represent a major step in AI development and are increasingly used in daily applications. However, they are prone to hallucinations, generating claims that contradict established facts, deviating from prompts, and producing inconsistent responses when the same prompt is presented multiple times. Addressing these issues is challenging due to the lack of comprehensive and easily assessable benchmark datasets. Most existing datasets are limited in scale and scope and rely on multiple-choice questions, which are insufficient for evaluating the generative capabilities of LLMs. To assess hallucination in LLMs, this paper introduces a comprehensive benchmark dataset consisting of over 20,000 unique prompts (more than 75,000 prompts in total) across eight domains. These prompts are designed to elicit definitive, concise, and informative answers. The dataset is divided into two segments: one publicly available for testing and assessing LLM performance, and a hidden segment for benchmarking various LLMs. In our experiments, we tested nine State-of-The-Art (SoTA) models, GPT-4o, GPT-3.5, LLama 2 7B, LLama 3 8B, Gemini 1.0 Pro, Mixtral 8x7B, Zephyr 7B, Deepseek-r1-7b, and Qwen2.5-14B, revealing that overall factual hallucination ranges from 48% to 82% on the public dataset and 31% to 76% on the hidden benchmark. Prompt Misalignment Hallucination ranges up to 95% in the public dataset and up to 94% in the hidden counterpart. Average consistency ranges from 21% to 61% and 44% to 63%, respectively. Domain-wise analysis reveals that LLM performance significantly deteriorates when asked for specific numeric information, whereas it performs moderately with queries involving persons, locations, and dates. Our dataset demonstrates its efficacy and serves as a comprehensive benchmark for evaluating LLM performance.<\/jats:p>","DOI":"10.3390\/info16110937","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T03:44:39Z","timestamp":1761795879000},"page":"937","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DefAn: Definitive Answer Dataset for LLM Hallucination Evaluation"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-4330","authenticated-orcid":false,"given":"A. B. M. Ashikur","family":"Rahman","sequence":"first","affiliation":[{"name":"Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saeed","family":"Anwar","sequence":"additional","affiliation":[{"name":"Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia"},{"name":"Department of Computer Science and Software Engineering, University of Western Australia, 35 Stirling Highway, Perth 6009, Australia"},{"name":"SDAIA-KFUPM Joint Research Center for Artificial Intelligence (JRC-AI), Dhahran 31261, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Usman","sequence":"additional","affiliation":[{"name":"Faculty of Science, Ontario Tech University, 2000 Simcoe Street North Oshawa, Oshawa, ON L1G 0C5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8311-1731","authenticated-orcid":false,"given":"Irfan","family":"Ahmad","sequence":"additional","affiliation":[{"name":"Information and Computer Science Department, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia"},{"name":"SDAIA-KFUPM Joint Research Center for Artificial Intelligence (JRC-AI), Dhahran 31261, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajmal","family":"Mian","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, University of Western Australia, 35 Stirling Highway, Perth 6009, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3744746","article-title":"A Comprehensive Overview of Large Language Models","volume":"16","author":"Naveed","year":"2025","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_2","unstructured":"Rawte, V., Sheth, A., and Das, A. (2023). A survey of hallucination in large foundation models. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Perkovi\u0107, G., Drobnjak, A., and Boti\u010dki, I. (2024, January 20\u201324). Hallucinations in llms: Understanding and addressing challenges. Proceedings of the 2024 47th MIPRO ICT and Electronics Convention (MIPRO), Opatija, Croatia.","DOI":"10.1109\/MIPRO60963.2024.10569238"},{"key":"ref_4","unstructured":"Lan, W., Chen, W., Chen, Q., Pan, S., Zhou, H., and Pan, Y. (2024). A Survey of Hallucination in Large Visual Language Models. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Hao, G., Wu, J., Pan, Q., and Morello, R. (2024). Quantifying the uncertainty of LLM hallucination spreading in complex adaptive social networks. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-66708-4"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref_7","unstructured":"Tonmoy, S., Zaman, S., Jain, V., Rani, A., Rawte, V., Chadha, A., and Das, A. (2024). A comprehensive survey of hallucination mitigation techniques in large language models. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Adlakha, V., BehnamGhader, P., Lu, X.H., Meade, N., and Reddy, S. (2023). Evaluating correctness and faithfulness of instruction-following models for question answering. arXiv.","DOI":"10.1162\/tacl_a_00667"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Muhlgay, D., Ram, O., Magar, I., Levine, Y., Ratner, N., Belinkov, Y., Abend, O., Leyton-Brown, K., Shashua, A., and Shoham, Y. (2023). Generating benchmarks for factuality evaluation of language models. arXiv.","DOI":"10.18653\/v1\/2024.eacl-long.4"},{"key":"ref_10","unstructured":"Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., and Chen, Y. (2023). Siren\u2019s song in the AI ocean: A survey on hallucination in large language models. arXiv."},{"key":"ref_11","unstructured":"Li, J., Consul, S., Zhou, E., Wong, J., Farooqui, N., Ye, Y., Manohar, N., Wei, Z., Wu, T., and Echols, B. (2024). Banishing LLM hallucinations requires rethinking generalization. arXiv."},{"key":"ref_12","unstructured":"Huang, L., Yu, W., Ma, W., Zhong, W., Feng, Z., Wang, H., Chen, Q., Peng, W., Feng, X., and Qin, B. (2023). A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv."},{"key":"ref_13","first-page":"4502","article-title":"Felm: Benchmarking factuality evaluation of large language models","volume":"36","author":"Zhao","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, X., Zhao, W.X., Nie, J.Y., and Wen, J.R. (2023, January 6\u201310). Halueval: A large-scale hallucination evaluation benchmark for large language models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"ref_15","unstructured":"Zhu, Z., Yang, Y., and Sun, Z. (2024). HaluEval-Wild: Evaluating Hallucinations of Language Models in the Wild. arXiv."},{"key":"ref_16","unstructured":"Thakur, A.S., Choudhary, K., Ramayapally, V.S., Vaidyanathan, S., and Hupkes, D. (2024). Judging the judges: Evaluating alignment and vulnerabilities in llms-as-judges. arXiv."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Chen, X., Wang, C., Xue, Y., Zhang, N., Yang, X., Li, Q., Shen, Y., Liang, L., Gu, J., and Chen, H. (2024). Unified hallucination detection for multimodal large language models. arXiv.","DOI":"10.18653\/v1\/2024.acl-long.178"},{"key":"ref_18","unstructured":"Luo, J., Li, T., Wu, D., Jenkin, M., Liu, S., and Dudek, G. (2024). Hallucination detection and hallucination mitigation: An investigation. arXiv."},{"key":"ref_19","unstructured":"Valentin, S., Fu, J., Detommaso, G., Xu, S., Zappella, G., and Wang, B. (2024). Cost-effective hallucination detection for llms. arXiv."},{"key":"ref_20","unstructured":"Mishra, A., Asai, A., Balachandran, V., Wang, Y., Neubig, G., Tsvetkov, Y., and Hajishirzi, H. (2024). Fine-grained hallucination detection and editing for language models. arXiv."},{"key":"ref_21","unstructured":"Hu, X., Ru, D., Qiu, L., Guo, Q., Zhang, T., Xu, Y., Luo, Y., Liu, P., Zhang, Y., and Zhang, Z. (2024). RefChecker: Reference-based Fine-grained Hallucination Checker and Benchmark for Large Language Models. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, S., Sun, R., and Wan, X. (2023). A new benchmark and reverse validation method for passage-level hallucination detection. arXiv.","DOI":"10.18653\/v1\/2023.findings-emnlp.256"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, Z., Das, K., Malin, B.A., and Kumar, S. (2023). SAC3: Reliable Hallucination Detection in Black-Box Language Models via Semantic-aware Cross-check Consistency. arXiv.","DOI":"10.18653\/v1\/2023.findings-emnlp.1032"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., and Evans, O. (2021). Truthfulqa: Measuring how models mimic human falsehoods. arXiv.","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"ref_25","unstructured":"Cheng, Q., Sun, T., Zhang, W., Wang, S., Liu, X., Zhang, M., He, J., Huang, M., Yin, Z., and Chen, K. (2023). Evaluating hallucinations in chinese large language models. arXiv."},{"key":"ref_26","first-page":"49025","article-title":"RealTime QA: What\u2019s the Answer Right Now?","volume":"36","author":"Kasai","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","unstructured":"Li, W., Li, L., Xiang, T., Liu, X., Deng, W., and Garcia, N. (2024). Can multiple-choice questions really be useful in detecting the abilities of LLMs?. arXiv."},{"key":"ref_28","unstructured":"Wang, H., Zhao, S., Qiang, Z., Xi, N., Qin, B., and Liu, T. (2024). LLMs May Perform MCQA by Selecting the Least Incorrect Option. arXiv."},{"key":"ref_29","unstructured":"Bang, S., Kim, M., Lee, H., and Choi, Y. (2025). HalluLens: A Fine-Grained Benchmark for Evaluating Intrinsic and Extrinsic Hallucinations in Large Language Models. arXiv."},{"key":"ref_30","unstructured":"Wang, X., Sun, R., Li, T., He, J., and Wan, X. (2025). HALoGEN: Fantastic LLM Hallucinations and Where to Find Them. arXiv."},{"key":"ref_31","unstructured":"Bao, J., Zhang, X., Wang, S., Liu, T., and Li, Z. (2024). FaithBench: A Diverse Hallucination Benchmark for Summarization Models. arXiv."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Molfese, F.M., Moroni, L., Gioffr\u00e8, L., Scir\u00e8, A., Conia, S., and Navigli, R. (2025). Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answering. arXiv.","DOI":"10.18653\/v1\/2025.findings-acl.950"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Li, N., Li, Y., Liu, Y., Shi, L., Wang, K., and Wang, H. (2024). HalluVault: A Novel Logic Programming-aided Metamorphic Testing Framework for Detecting Fact-Conflicting Hallucinations in Large Language Models. arXiv.","DOI":"10.1145\/3689776"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, J., Ren, R., Cheng, X., Zhao, W.X., Nie, J.Y., and Wen, J.R. (2024). The dawn after the dark: An empirical study on factuality hallucination in large language models. arXiv.","DOI":"10.18653\/v1\/2024.acl-long.586"},{"key":"ref_35","unstructured":"Fourrier, C., Habib, N., Lozovskaya, A., Szafer, K., and Wolf, T. (2025, September 05). Performances Are Plateauing, Let\u2019s Make the Leaderboard Steep Again. Available online: https:\/\/huggingface.co\/spaces\/open-llm-leaderboard\/blog."},{"key":"ref_36","unstructured":"Tunstall, L., Beeching, E., Lambert, N., Rajani, N., Huang, S., Rasul, K., Rush, A.M., and Wolf, T. (2025, July 25). The Alignment Handbook. Available online: https:\/\/github.com\/huggingface\/alignment-handbook."},{"key":"ref_37","unstructured":"Jiang, A.Q., Sablayrolles, A., Roux, A., Mensch, A., Savary, B., Bamford, C., Chaplot, D.S., Casas, D.d.l., Hanna, E.B., and Bressand, F. (2024). Mixtral of experts. arXiv."},{"key":"ref_38","unstructured":"OpenAI (2024, June 05). ChatGPT. Available online: https:\/\/openai.com\/."},{"key":"ref_39","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., and Bhosale, S. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv."},{"key":"ref_40","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., and Bhosale, S. (2024, June 05). Meta Llama 3. Available online: https:\/\/github.com\/meta-llama\/llama3."},{"key":"ref_41","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). Gpt-4 technical report. arXiv."},{"key":"ref_42","unstructured":"Deepmind, G. (2024, June 05). Google AI for Developers. Available online: https:\/\/ai.google.dev\/gemini-api\/docs\/models\/gemini."},{"key":"ref_43","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., Zhang, R., Xu, R., Zhu, Q., Ma, S., Wang, P., and Bi, X. (2025). Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv."},{"key":"ref_44","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., and Wei, H. (2024). Qwen2. 5 Technical Report. arXiv."},{"key":"ref_45","unstructured":"He, H., and Lab, T.M. (2025, September 05). Defeating Nondeterminism in LLM Inference. Thinking Machines Lab: Connectionism, Available online: https:\/\/thinkingmachines.ai\/blog\/defeating-nondeterminism-in-llm-inference\/."},{"key":"ref_46","unstructured":"Sharma, M., Tong, M., Korbak, T., Duvenaud, D., Askell, A., Bowman, S.R., Cheng, N., Durmus, E., Hatfield-Dodds, Z., and Johnston, S.R. (2023). Towards understanding sycophancy in language models. arXiv."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/11\/937\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T04:04:26Z","timestamp":1761797066000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/11\/937"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":46,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["info16110937"],"URL":"https:\/\/doi.org\/10.3390\/info16110937","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,28]]}}}