{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T10:03:38Z","timestamp":1776679418097,"version":"3.51.2"},"publisher-location":"Singapore","reference-count":41,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570775","type":"print"},{"value":"9789819570782","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-7078-2_8","type":"book-chapter","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:18:43Z","timestamp":1776676723000},"page":"107-124","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Do the\u00a0Instruction-Fine-Tuned Large Language Models Challenge Flawed Instructions? A Study on\u00a0Over-Compliance and\u00a0Hallucinations"],"prefix":"10.1007","author":[{"given":"Xiaolu","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxiang","family":"Shang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"8_CR1","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 1877\u20131901. Curran Associates, Inc. (2020)"},{"issue":"70","key":"8_CR2","first-page":"1","volume":"25","author":"HW Chung","year":"2024","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. J. Mach. Learn. Res. 25(70), 1\u201353 (2024)","journal-title":"J. Mach. Learn. Res."},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Dong, Z., Zhou, Z., Yang, C., Shao, J., Qiao, Y.: Attacks, defenses and evaluations for LLM conversation safety: a survey. arXiv preprint arXiv:2402.09283 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.375"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Fanous, A., et al.: Syceval: Evaluating LLM sycophancy. arXiv preprint arXiv:2502.08177 (2025)","DOI":"10.1609\/aies.v8i1.36598"},{"key":"8_CR5","unstructured":"Friel, R., Sanyal, A.: Chainpoll: a high efficacy method for LLM hallucination detection. arXiv preprint arXiv:2310.18344 (2023)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Gehman, S., Gururangan, S., Sap, M., Choi, Y., Smith, N.A.: Realtoxicityprompts: evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, P., Jiao, C., Yeh, Y.T., Mehri, S., Eskenazi, M., Bigham, J.P.: Instructdial: improving zero and few-shot generalization in dialogue through instruction tuning. arXiv preprint arXiv:2205.12673 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.33"},{"key":"8_CR8","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: International Conference on Learning Representations (2021)"},{"key":"8_CR9","unstructured":"Huang, L., et\u00a0al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232 (2023)"},{"key":"8_CR10","unstructured":"Kirichenko, P., Ibrahim, M., Chaudhuri, K., Bell, S.J.: Abstentionbench: reasoning LLMs fail on unanswerable questions. arXiv preprint arXiv:2506.09038 (2025)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Cheng, X., Zhao, W.X., Nie, J.Y., Wen, J.R.: Halueval: a large-scale hallucination evaluation benchmark for large language models. arXiv preprint arXiv:2305.11747 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"issue":"OOPSLA2","key":"8_CR12","doi-asserted-by":"publisher","first-page":"1843","DOI":"10.1145\/3689776","volume":"8","author":"N Li","year":"2024","unstructured":"Li, N., Li, Y., Liu, Y., Shi, L., Wang, K., Wang, H.: Drowzee: metamorphic testing for fact-conflicting hallucination detection in large language models. Proc. ACM Program. Lang. 8(OOPSLA2), 1843\u20131872 (2024)","journal-title":"Proc. ACM Program. Lang."},{"key":"8_CR13","unstructured":"Lin, S., Hilton, J., Evans, O.: Truthfulqa: measuring how models mimic human falsehoods. CoRR abs\/2109.07958 (2021)"},{"key":"8_CR14","unstructured":"Liu, F.W., Hu, C.: Exploring vulnerabilities and protections in large language models: a survey. arXiv preprint arXiv:2406.00240 (2024)"},{"issue":"9","key":"8_CR15","first-page":"1","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: WebGLM: towards an efficient web-enhanced question answering system with human preferences. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 4549\u20134560 (2023)","DOI":"10.1145\/3580305.3599931"},{"key":"8_CR17","unstructured":"Longpre, S., et\u00a0al.: The flan collection: designing data and methods for effective instruction tuning. In: International Conference on Machine Learning, pp. 22631\u201322648. PMLR (2023)"},{"key":"8_CR18","unstructured":"Luo, Z., et al.: Wizardcoder: empowering code large language models with evol-instruct. arXiv preprint arXiv:2306.08568 (2023)"},{"key":"8_CR19","unstructured":"Mazeika, M., et\u00a0al.: Harmbench: a standardized evaluation framework for automated red teaming and robust refusal. arXiv preprint arXiv:2402.04249 (2024)"},{"key":"8_CR20","unstructured":"Mishra, A., et al.: Fine-grained hallucination detection and editing for language models. arXiv preprint arXiv:2401.06855 (2024)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 27730\u201327744. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-2011"},{"key":"8_CR22","unstructured":"Pastorino, V., Sivakumar, J.A., Moosavi, N.S.: Decoding news narratives: a critical analysis of large language models in framing bias detection. arXiv preprint arXiv:2402.11621 (2024)"},{"key":"8_CR23","unstructured":"Peng, B., Li, C., He, P., Galley, M., Gao, J.: Instruction tuning with GPT-4 (2023)"},{"key":"8_CR24","unstructured":"Perez, E., et\u00a0al.: Discovering language model behaviors with model-written evaluations. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 13387\u201313434 (2023)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Rrv, A., Tyagi, N., Uddin, M.N., Varshney, N., Baral, C.: Chaos with keywords: exposing large language models sycophantic hallucination to misleading keywords and evaluating defense strategies. arXiv preprint arXiv:2406.03827 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.755"},{"key":"8_CR26","unstructured":"Sclar, M., Choi, Y., Tsvetkov, Y., Suhr, A.: Quantifying language models\u2019 sensitivity to spurious features in prompt design or: how I learned to start worrying about prompt formatting. arXiv preprint arXiv:2310.11324 (2023)"},{"key":"8_CR27","unstructured":"Sharma, M., et\u00a0al.: Towards understanding sycophancy in language models. arXiv preprint arXiv:2310.13548 (2023)"},{"key":"8_CR28","unstructured":"Sun, L., et\u00a0al.: TrustLLM: trustworthiness in large language models. arXiv preprint arXiv:2401.05561 (2024)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Sun, Y., Yin, Z., Guo, Q., Wu, J., Qiu, X., Zhao, H.: Benchmarking hallucination in large language models based on unanswerable math word problem. arXiv preprint arXiv:2403.03558 (2024)","DOI":"10.63317\/3jovt56oiu3g"},{"key":"8_CR30","unstructured":"Tannen, D.: Framing in Discourse. Oxford University Press (1993)"},{"key":"8_CR31","unstructured":"Wang, X., et al.: Instructuie: multi-task instruction tuning for unified information extraction. arXiv preprint arXiv:2304.08085 (2023)"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 24824\u201324837. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-1800"},{"key":"8_CR33","unstructured":"Wei, J., Huang, D., Lu, Y., Zhou, D., Le, Q.V.: Simple synthetic data reduces sycophancy in large language models. arXiv preprint arXiv:2308.03958 (2023)"},{"key":"8_CR34","unstructured":"Wen, J., et al.: Language models learn to mislead humans via RLHF. arXiv preprint arXiv:2409.12822 (2024)"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Yao, P., Barbosa, D.: Accurate and nuanced open-QA evaluation through textual entailment. arXiv preprint arXiv:2405.16702 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.151"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Yu, Q.: \u201cAgain, dozens of refugees drowned\u201d: a computational study of political framing evoked by presuppositions. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pp. 31\u201343 (2022)","DOI":"10.18653\/v1\/2022.naacl-srw.5"},{"key":"8_CR37","unstructured":"Zhang, S., et\u00a0al.: Instruction tuning for large language models: a survey. arXiv preprint arXiv:2308.10792 (2023)"},{"key":"8_CR38","doi-asserted-by":"publisher","unstructured":"Zhang, Z., et al.: SafetyBench: evaluating the safety of large language models. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 15537\u201315553. Association for Computational Linguistics, Bangkok, Thailand (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.830","DOI":"10.18653\/v1\/2024.acl-long.830"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Zhong, W., et al.: Agieval: a human-centric benchmark for evaluating foundation models (2023)","DOI":"10.18653\/v1\/2024.findings-naacl.149"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Zhu, K., et\u00a0al.: Promptrobust: towards evaluating the robustness of large language models on adversarial prompts. In: Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis, pp. 57\u201368 (2023)","DOI":"10.1145\/3689217.3690621"},{"key":"8_CR41","unstructured":"Zou, A., Wang, Z., Carlini, N., Nasr, M., Kolter, J.Z., Fredrikson, M.: Universal and transferable adversarial attacks on aligned language models. arXiv preprint arXiv:2307.15043 (2023)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7078-2_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T09:19:15Z","timestamp":1776676755000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7078-2_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570775","9789819570782"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7078-2_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"21 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that\u00a0are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}