{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:14:30Z","timestamp":1773778470969,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031808883","type":"print"},{"value":"9783031808890","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-80889-0_8","type":"book-chapter","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T08:44:07Z","timestamp":1737708247000},"page":"114-130","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["LLMs Can Check Their Own Results to\u00a0Mitigate Hallucinations in\u00a0Traffic Understanding Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3812-5466","authenticated-orcid":false,"given":"Malsha Ashani Mahawatta","family":"Dona","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5275-8372","authenticated-orcid":false,"given":"Beatriz","family":"Cabrero-Daniel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3221-7517","authenticated-orcid":false,"given":"Yinan","family":"Yu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4828-1150","authenticated-orcid":false,"given":"Christian","family":"Berger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,25]]},"reference":[{"key":"8_CR1","unstructured":"BMW intelligent personal assistant powered by the Alexa large language model (LLM) (2024). https:\/\/tinyurl.com\/BMWweb. Accessed 26 Feb 2024"},{"key":"8_CR2","unstructured":"Hello GPT-4o (2024). https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed 15 May 2024"},{"key":"8_CR3","unstructured":"Brown, T., et\u00a0al.: 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). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"8_CR4","unstructured":"Chen, X., et al.: Unified hallucination detection for multimodal large language models. arXiv preprint: arXiv:2402.03190 (2024)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cole, J.R., Zhang, M.J., Gillick, D., Eisenschlos, J.M., Dhingra, B., Eisenstein, J.: Selectively answering ambiguous questions. arXiv preprint: arXiv:2305.14613 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.35"},{"key":"8_CR6","unstructured":"Deng, A., Chen, Z., Hooi, B.: Seeing is believing: mitigating hallucination in large vision-language models via clip-guided decoding. arXiv:2402.15300 (2024)"},{"key":"8_CR7","unstructured":"Elaraby, M., Lu, M., Dunn, J., Zhang, X., Wang, Y., Liu, S.: Halo: estimation and reduction of hallucinations in open-source weak large language models. arXiv preprint: arXiv:2308.11764 (2023)"},{"key":"8_CR8","unstructured":"Es, S., James, J., Espinosa-Anke, L., Schockaert, S.: RAGAS: automated evaluation of retrieval augmented generation. arXiv preprint: arXiv:2309.15217 (2023)"},{"key":"8_CR9","unstructured":"Feldt, R., Magazinius, A.: Validity threats in empirical software engineering research - an initial survey, pp. 374\u2013379 (2010)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Guan, X., et\u00a0al.: Mitigating large language model hallucinations via autonomous knowledge graph-based retrofitting. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 18126\u201318134 (2024)","DOI":"10.1609\/aaai.v38i16.29770"},{"key":"8_CR11","unstructured":"Guo, Z., et al.: Evaluating large language models: a comprehensive survey (2023). https:\/\/arxiv.org\/abs\/2310.19736"},{"key":"8_CR12","unstructured":"Hartvigsen, T., Sankaranarayanan, S., Palangi, H., Kim, Y., Ghassemi, M.: Aging with grace: lifelong model editing with discrete key-value adaptors. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Huang, L., et\u00a0al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions (2023)","DOI":"10.1145\/3703155"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Ji, Z., Yu, T., Xu, Y., Lee, N., Ishii, E., Fung, P.: Towards mitigating LLM hallucination via self reflection. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 1827\u20131843 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Lebret, R., Grangier, D., Auli, M.: Neural text generation from structured data with application to the biography domain (2016). https:\/\/arxiv.org\/abs\/1603.07771","DOI":"10.18653\/v1\/D16-1128"},{"key":"8_CR16","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems, vol.\u00a036, pp. 34892\u201334916. Curran Associates, Inc. (2023). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Manakul, P., Liusie, A., Gales, M.J.: SELFCHECKGPT: zero-resource black-box hallucination detection for generative large language models. arXiv:2303.08896 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.557"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Ronanki, K., Cabrero-Daniel, B., Berger, C.: Chatgpt as a tool for user story quality evaluation: trustworthy out of the box? In: International Conference on Agile Software Development, pp. 173\u2013181. Springer (2022)","DOI":"10.1007\/978-3-031-48550-3_17"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Rony, M.R.A.H., et al.: CarExpert: leveraging large language models for in-car conversational question answering (2023)","DOI":"10.18653\/v1\/2023.emnlp-industry.56"},{"key":"8_CR20","unstructured":"Sun, G., et al.: CrossCheckGPT: universal hallucination ranking for multimodal foundation models. arXiv preprint: arXiv:2405.13684 (2024)"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"8_CR22","unstructured":"Tonmoy, S.M.T.I., et al.: A comprehensive survey of hallucination mitigation techniques in large language models (2024). https:\/\/arxiv.org\/abs\/2401.01313"},{"key":"8_CR23","unstructured":"Wang, S., et al.: Large language models for education: a survey and outlook. arXiv:2403.18105 (2024)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Logical closed loop: uncovering object hallucinations in large vision-language models. arXiv preprint: arXiv:2402.11622 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.414"},{"key":"8_CR25","unstructured":"Yu, W., Zhang, Z., Liang, Z., Jiang, M., Sabharwal, A.: Improving language models via plug-and-play retrieval feedback. arXiv preprint: arXiv:2305.14002 (2023)"},{"key":"8_CR26","unstructured":"Yu, Y., Scheidegger, S., Bakker, J.: Safety-driven data labelling platform to enable safe and responsible AI (2021). https:\/\/trid.trb.org\/View\/1948943"}],"container-title":["Lecture Notes in Computer Science","Testing Software and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-80889-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T08:44:23Z","timestamp":1737708263000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-80889-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031808883","9783031808890"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-80889-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICTSS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP International Conference on Testing Software and Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pts2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conf.researchr.org\/home\/ictss-2024","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}