{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T06:45:57Z","timestamp":1785653157699,"version":"3.56.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032316653","type":"print"},{"value":"9783032316660","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"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":[[2027]]},"DOI":"10.1007\/978-3-032-31666-0_4","type":"book-chapter","created":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:46:57Z","timestamp":1785649617000},"page":"49-63","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["When Not to\u00a0Answer: Evaluating Prompts on\u00a0Reasoning Models for\u00a0Effective Abstention in\u00a0Unanswerable Math Word Problems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2495-6474","authenticated-orcid":false,"given":"Asir","family":"Saadat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7728-5532","authenticated-orcid":false,"given":"Tasmia Binte","family":"Sogir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1445-693X","authenticated-orcid":false,"given":"Md. Taukir Azam","family":"Chowdhury","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7576-3780","authenticated-orcid":false,"given":"Syem","family":"Aziz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"issue":"4","key":"4_CR1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.21659\/rupkatha.v15n4.17","volume":"15","author":"Z Ahmad","year":"2023","unstructured":"Ahmad, Z., Kaiser, W., Rahim, S.: Hallucinations in chatgpt: an unreliable tool for learning. Rupkatha J. Interdisciplinary Stud. Humanities 15(4), 12 (2023)","journal-title":"Rupkatha J. Interdisciplinary Stud. Humanities"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Ahn, J., Verma, R., Lou, R., Liu, D., Zhang, R., Yin, W.: Large language models for mathematical reasoning: Progresses and challenges (2024). arXiv preprint arXiv:2402.00157","DOI":"10.18653\/v1\/2024.eacl-srw.17"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Alkaissi, H., McFarlane, S.I.: Artificial hallucinations in chatgpt: implications in scientific writing. Cureus 15(2) (2023)","DOI":"10.7759\/cureus.35179"},{"key":"4_CR4","unstructured":"Anagnostidis, S., Bulian, J.: How susceptible are llms to influence in prompts? arXiv preprint arXiv:2408.11865 (2024)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Balepur, N., Ravichander, A., Rudinger, R.: Artifacts or abduction: how do llms answer multiple-choice questions without the question?, arXiv preprint arXiv:2402.12483 (2024)","DOI":"10.18653\/v1\/2024.acl-long.555"},{"key":"4_CR6","unstructured":"Beeching, E., et al.: Numinamath 7b tir (2024). https:\/\/huggingface.co\/AI-MO\/NuminaMath-7B-TIR"},{"key":"4_CR7","unstructured":"Bommasani, R., et al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"4_CR8","unstructured":"Tom, B., Brown: language models are few-shot learners, arXiv preprint arXiv:2005.14165 (2020)"},{"issue":"1","key":"4_CR9","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/s11528-023-00896-0","volume":"68","author":"W Cain","year":"2024","unstructured":"Cain, W.: Prompting change: exploring prompt engineering in large language model ai and its potential to transform education. TechTrends 68(1), 47\u201357 (2024)","journal-title":"TechTrends"},{"key":"4_CR10","unstructured":"Chang, K., Xu, S., Wang, C., Luo, Y., Xiao, T., Zhu, J.: Efficient prompting methods for large language models: a survey (2024). http:\/\/arxiv.org\/abs\/2404.01077"},{"key":"4_CR11","unstructured":"Chen, B., Zhang, Z., Langren\u00e9, N., Zhu, S.: Unleashing the potential of prompt engineering in large language models: a comprehensive review (2024a). http:\/\/arxiv.org\/abs\/2310.14735"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Chen, K., Shao, A., Burapacheep, J., Li, Y.: Conversational ai and equity through assessing gpt-3\u2019s communication with diverse social groups on contentious topics. Sci. Rep. 14(1), 1561 (2024b)","DOI":"10.1038\/s41598-024-51969-w"},{"key":"4_CR13","unstructured":"Chen, W., Ma, X., Wang, X., Cohen, W.W.: Program of thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks, arXiv preprint arXiv:2211.12588 (2022)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Deng, Y., Zhao, Y., Li, M., Ng, S.-K., Chua, T.-S.: Don\u2019t just say \u201ci don\u2019t know\u201d ! self-aligning large language models for responding to unknown questions with explanations (2024a). http:\/\/arxiv.org\/abs\/2402.15062","DOI":"10.18653\/v1\/2024.emnlp-main.757"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Deng, Y., Zhao, Y., Li, M., Ng, S.-K., Chua, T.-S.: Gotcha! don\u2019t trick me with unanswerable questions! self-aligning large language models for responding to unknown questions (2024b). arXiv preprint arXiv:2402.15062","DOI":"10.18653\/v1\/2024.emnlp-main.757"},{"issue":"8017","key":"4_CR16","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1038\/s41586-024-07421-0","volume":"630","author":"S Farquhar","year":"2024","unstructured":"Farquhar, S., Kossen, J., Kuhn, L., Gal, Y.: Detecting hallucinations in large language models using semantic entropy. Nature 630(8017), 625\u2013630 (2024)","journal-title":"Nature"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Frieder, S., et al.:. Mathematical capabilities of chatgpt. Adv. Neural Inform. Process. Syst. 36 (2024)","DOI":"10.52202\/075280-1205"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Guo, Y., Jiao, F., Shen, Z., Nie, L., Kankanhalli, M.: Unk-vqa: A dataset and a probe into the abstention ability of multi-modal large models (2024). http:\/\/arxiv.org\/abs\/2310.10942","DOI":"10.1109\/TPAMI.2024.3437288"},{"key":"4_CR19","unstructured":"Hariri, W.: Unlocking the potential of chatgpt: a comprehensive exploration of its applications, advantages, limitations, and future directions in natural language processing, arXiv preprint arXiv:2304.02017 (2023)"},{"key":"4_CR20","unstructured":"Hendrycks, D., et al.:. Measuring mathematical problem solving with the math dataset, arXiv preprint arXiv:2103.03874 (2021)"},{"issue":"4","key":"4_CR21","first-page":"1148","volume":"13","author":"J Huang","year":"2023","unstructured":"Huang, J., Tan, M.: The role of chatgpt in scientific communication: writing better scientific review articles. Am. J. Cancer Res. 13(4), 1148 (2023)","journal-title":"Am. J. Cancer Res."},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Imani, S., Du, L., Shrivastava, H.: Mathprompter: mathematical reasoning using large language models, arXiv preprint arXiv:2303.05398 (2023)","DOI":"10.18653\/v1\/2023.acl-industry.4"},{"key":"4_CR23","unstructured":"Kong, A., et al. Better zero-shot reasoning with role-play prompting. arXiv preprint arXiv:2308.07702 (2023)"},{"key":"4_CR24","unstructured":"Li, Z.: The dark side of chatgpt: legal and ethical challenges from stochastic parrots and hallucination, arXiv preprint arXiv:2304.14347 (2023)"},{"key":"4_CR25","unstructured":"Lingo, R.: The role of chatgpt in democratizing data science: an exploration of ai-facilitated data analysis in telematics, arXiv preprint (2023). arXiv:2308.02045 (2023)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Summary of chatgpt-related research and perspective towards the future of large language models. Meta-Radiol., 100017 (2023a)","DOI":"10.1016\/j.metrad.2023.100017"},{"key":"4_CR27","unstructured":"Liu, Y., Singh, A., Freeman, C.D., Co-Reyes, J.D., Liu, P.J.: Improving large language model fine-tuning for solving math problems (2023b). http:\/\/arxiv.org\/abs\/2310.10047"},{"key":"4_CR28","unstructured":"Liu, Y., Singh, A., Freeman, C.D., Co-Reyes, J.D., Liu, P.J.: Improving large language model fine-tuning for solving math problems. arXiv preprint arXiv:2310.10047 (2023c)"},{"key":"4_CR29","unstructured":"Van Long, P.P., Vu, D.A., Hoang, N.M., Do, X.L., Luu, A.T.: Chatgpt as a math questioner? evaluating chatgpt on generating pre-university math questions (2024). http:\/\/arxiv.org\/abs\/2312.01661"},{"key":"4_CR30","unstructured":"Ma, J., Dai, D., Sui, Z.: Large language models are unconscious of unreasonability in math problems, arXiv preprint arXiv:2403.19346 (2024)"},{"key":"4_CR31","unstructured":"Madhusudhan, N., Madhusudhan, S.T., Yadav, V., Hashemi, M.: Do llms know when to not answer? investigating abstention abilities of large language models. arXiv preprint arXiv:2407.16221 (2024a)"},{"key":"4_CR32","unstructured":"Madhusudhan, N., Madhusudhan, S.T., Yadav, V., Hashemi, M.:. Do llms know when to not answer? investigating abstention abilities of large language models (2024b). http:\/\/arxiv.org\/abs\/2407.16221"},{"key":"4_CR33","unstructured":"OpenAI. 2024. Openai api documentation. https:\/\/platform.openai.com\/docs\/. Accessed 13 Oct 2024"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Pan, Y., Pan, L., Chen, W., Nakov, P., Kan, M.-Y., Wang, Y.: On the risk of misinformation pollution with large language models. arXiv preprint arXiv:2305.13661 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.97"},{"key":"4_CR35","unstructured":"Shakarian, P., Koyyalamudi, A., Ngu, N., Mareedu, L.: An independent evaluation of chatgpt on mathematical word problems (mwp), arXiv preprint arXiv:2302.13814 (2023)"},{"key":"4_CR36","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":"4_CR37","doi-asserted-by":"crossref","unstructured":"Tao, S., et al.: When to trust llms: Aligning confidence with response quality, arXiv preprint. arXiv:2404.17287 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.357"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: A systematic review of chatgpt and other conversational large language models in healthcare. medRxiv (2024a)","DOI":"10.1101\/2024.04.26.24306390"},{"key":"4_CR39","unstructured":"Wang, Z., Kodner, J., Rambow, O.: Evaluating llms with multiple problems at once: A new paradigm for probing llm capabilities. arXiv preprint arXiv:2406.10786 (2024b)"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Wardat, Y., Tashtoush, M.A., AlAli, R., Jarrah, A.M.: Chatgpt: a revolutionary tool for teaching and learning mathematics. Eurasia J. Math. Sci. Technol. Educ. 19(7), em2286 (2023)","DOI":"10.29333\/ejmste\/13272"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, vol. 35, pp. 24824\u201324837 (2022)","DOI":"10.52202\/068431-1800"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Xiao, C., Xu, S.X., Zhang, K., Wang, Y., Xia, L.: Evaluating reading comprehension exercises generated by llms: A showcase of chatgpt in education applications. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023),pp. 610\u2013625 (2023)","DOI":"10.18653\/v1\/2023.bea-1.52"},{"key":"4_CR43","unstructured":"Miao Xiong, M., et al.: Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms. arXiv preprint arXiv:2306.13063 (2023)"},{"key":"4_CR44","unstructured":"Xu, X., Xiao, T., Chao, Z., Huang, Z., Yang, C., Wang, Y.:. Can llms solve longer math word problems better? arXiv preprint arXiv:2405.14804 (2024a)"},{"key":"4_CR45","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Chatglm-math: Improving math problem-solving in large language models with a self-critique pipeline (2024b). http:\/\/arxiv.org\/abs\/2404.02893","DOI":"10.18653\/v1\/2024.findings-emnlp.569"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, Z., et al.: Mathattack: Attacking large language models towards math solving ability. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.38, pp. 19750\u201319758 (2024)","DOI":"10.1609\/aaai.v38i17.29949"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-31666-0_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,2]],"date-time":"2026-08-02T05:47:01Z","timestamp":1785649621000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-31666-0_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,3]]},"ISBN":["9783032316653","9783032316660"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-31666-0_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,3]]},"assertion":[{"value":"3 August 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lyon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 August 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}