{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T02:07:23Z","timestamp":1783649243085,"version":"3.55.0"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031472398","type":"print"},{"value":"9783031472404","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-47240-4_19","type":"book-chapter","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T08:02:40Z","timestamp":1698825760000},"page":"348-367","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":78,"title":["Can ChatGPT Replace Traditional KBQA Models? An\u00a0In-Depth Analysis of\u00a0the\u00a0Question Answering Performance of\u00a0the\u00a0GPT LLM Family"],"prefix":"10.1007","author":[{"given":"Yiming","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dehai","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongrui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guilin","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"19_CR1","unstructured":"Bai, Y., et al.: Benchmarking foundation models with language-model-as-an-examiner. arXiv preprint arXiv:2306.04181 (2023)"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Bang, Y., et al.: A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity. arXiv e-prints, arXiv-2302 (2023)","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"19_CR3","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1162\/tacl_a_00254","volume":"7","author":"Y Belinkov","year":"2019","unstructured":"Belinkov, Y., Glass, J.: Analysis methods in neural language processing: a survey. Trans. Assoc. Comput. Linguist. 7, 49\u201372 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Cao, S., et al.: KQA Pro: a dataset with explicit compositional programs for complex question answering over knowledge base. In: Proceedings ACL Conference, pp. 6101\u20136119 (2022)","DOI":"10.18653\/v1\/2022.acl-long.422"},{"key":"19_CR6","unstructured":"Chang, Y., et al.: A survey on evaluation of large language models. arXiv preprint arXiv:2307.03109 (2023)"},{"key":"19_CR7","unstructured":"Chen, X., et al.: How robust is GPT-3.5 to predecessors? A comprehensive study on language understanding tasks. arXiv e-prints, arXiv-2303 (2023)"},{"key":"19_CR8","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. arXiv e-prints, arXiv-2204 (2022)"},{"key":"19_CR9","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"19_CR10","unstructured":"Fu, C., et al.: MME: a comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)"},{"key":"19_CR11","unstructured":"Fu, Y., Peng, H., Khot, T.: How does GPT obtain its ability? Tracing emergent abilities of language models to their sources. Yao Fu\u2019s Notion (2022)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Y., et al.: Beyond IID: three levels of generalization for question answering on knowledge bases. In: Proceedings WWW Conference, pp. 3477\u20133488 (2021)","DOI":"10.1145\/3442381.3449992"},{"key":"19_CR13","unstructured":"Gu, Y., Su, Y.: ArcaneQA: dynamic program induction and contextualized encoding for knowledge base question answering. In: Proceedings COLING Conference, pp. 1718\u20131731 (2022)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"He, H., Choi, J.D.: The stem cell hypothesis: dilemma behind multi-task learning with transformer encoders. In: Proceedings EMNLP Conference, pp. 5555\u20135577 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.451"},{"key":"19_CR15","unstructured":"Hu, X., Wu, X., Shu, Y., Qu, Y.: Logical form generation via multi-task learning for complex question answering over knowledge bases. In: Proceedings ICCL Conference, pp. 1687\u20131696 (2022)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Huang, F., Kwak, H., An, J.: Is ChatGPT better than human annotators? Potential and limitations of ChatGPT in explaining implicit hate speech. arXiv e-prints, arXiv-2302 (2023)","DOI":"10.1145\/3543873.3587368"},{"key":"19_CR17","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1162\/tacl_a_00324","volume":"8","author":"Z Jiang","year":"2020","unstructured":"Jiang, Z., Xu, F.F., Araki, J., Neubig, G.: How can we know what language models know? Trans. Assoc. Comput. Linguist. 8, 423\u2013438 (2020)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR18","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings NAACL-HLT Conference, pp. 4171\u20134186 (2019)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Koco\u0144, J., et al.: ChatGPT: jack of all trades, master of none. arXiv e-prints, arXiv-2302 (2023)","DOI":"10.2139\/ssrn.4372889"},{"key":"19_CR20","unstructured":"Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners. arXiv preprint arXiv:2205.11916 (2022)"},{"key":"19_CR21","unstructured":"Liang, P., et al.: Holistic evaluation of language models. arXiv e-prints, arXiv-2211 (2022)"},{"key":"19_CR22","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1162\/tacl_a_00433","volume":"9","author":"S Longpre","year":"2021","unstructured":"Longpre, S., Lu, Y., Daiber, J.: MKQA: a linguistically diverse benchmark for multilingual open domain question answering. Trans. Assoc. Comput. Linguist. 9, 1389\u20131406 (2021)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"19_CR23","unstructured":"Lyu, C., Xu, J., Wang, L.: New trends in machine translation using large language models: case examples with ChatGPT. arXiv preprint arXiv:2305.01181 (2023)"},{"key":"19_CR24","unstructured":"Ngomo, N.: 9th challenge on question answering over linked data (QALD-9). Language 7(1), 58\u201364 (2018)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Nie, L., et al.: GraphQ IR: unifying the semantic parsing of graph query languages with one intermediate representation. In: Proceedings EMNLP Conference, pp. 5848\u20135865 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.394"},{"key":"19_CR26","unstructured":"Omar, R., Mangukiya, O., Kalnis, P., Mansour, E.: ChatGPT versus traditional question answering for knowledge graphs: current status and future directions towards knowledge graph chatbots. arXiv e-prints, arXiv-2302 (2023)"},{"key":"19_CR27","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"19_CR28","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. arXiv e-prints, arXiv-2203 (2022)"},{"key":"19_CR29","unstructured":"Perevalov, A., Yan, X., Kovriguina, L., Jiang, L., Both, A., Usbeck, R.: Knowledge graph question answering leaderboard: a community resource to prevent a replication crisis. In: Proceedings LREC Conference, pp. 2998\u20133007 (2022)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Petroni, F., et al.: Language models as knowledge bases? In: Proceedings IJCAI Conference, pp. 2463\u20132473 (2019)","DOI":"10.18653\/v1\/D19-1250"},{"key":"19_CR31","unstructured":"Pramanik, S., Alabi, J., Saha Roy, R., Weikum, G.: UNIQORN: unified question answering over RDF knowledge graphs and natural language text. arXiv e-prints, arXiv-2108 (2021)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Purkayastha, S., Dana, S., Garg, D., Khandelwal, D., Bhargav, G.S.: A deep neural approach to KGQA via SPARQL silhouette generation. In: Proceedings IJCNN Conference, pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892263"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Qin, C., Zhang, A., Zhang, Z., Chen, J., Yasunaga, M., Yang, D.: Is ChatGPT a general-purpose natural language processing task solver? arXiv e-prints, arXiv-2302 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.85"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Qin, G., Eisner, J.: Learning how to ask: querying LMS with mixtures of soft prompts. In: Proceedings NAACL-HLT Conference (2021)","DOI":"10.18653\/v1\/2021.naacl-main.410"},{"key":"19_CR35","unstructured":"Rae, J.W., et al.: Scaling language models: methods, analysis & insights from training gopher. arXiv e-prints, arXiv-2112 (2021)"},{"issue":"1","key":"19_CR36","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Reynolds, L., McDonell, K.: Prompt programming for large language models: beyond the few-shot paradigm. In: Proceedings CHI EA Conference, pp. 1\u20137 (2021)","DOI":"10.1145\/3411763.3451760"},{"key":"19_CR38","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Wu, T., Guestrin, C., Singh, S.: Beyond accuracy: behavioral testing of NLP models with checklist. In: Proceedings ACL Conference, pp. 4902\u20134912 (2020)","DOI":"10.18653\/v1\/2020.acl-main.442"},{"key":"19_CR39","doi-asserted-by":"crossref","unstructured":"Rychalska, B., Basaj, D., Gosiewska, A., Biecek, P.: Models in the wild: on corruption robustness of neural NLP systems. In: Proceedings ICONIP Conference, pp. 235\u2013247 (2019)","DOI":"10.1007\/978-3-030-36718-3_20"},{"issue":"9","key":"19_CR40","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1109\/TSE.2016.2532875","volume":"42","author":"S Segura","year":"2016","unstructured":"Segura, S., Fraser, G., Sanchez, A.B., Ruiz-Cort\u00e9s, A.: A survey on metamorphic testing. IEEE Trans. Software Eng. 42(9), 805\u2013824 (2016)","journal-title":"IEEE Trans. Software Eng."},{"key":"19_CR41","unstructured":"Srivastava, A., et al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022)"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Su, Y., et al.: On generating characteristic-rich question sets for QA evaluation. In: Proceedings EMNLP Conference, pp. 562\u2013572 (2016)","DOI":"10.18653\/v1\/D16-1054"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Talmor, A., Berant, J.: The web as a knowledge-base for answering complex questions. In: Proceedings ACL Conference, pp. 641\u2013651 (2018)","DOI":"10.18653\/v1\/N18-1059"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Tjong Kim Sang, E.F., De Meulder, F.: Introduction to the CoNLL-2003 shared task: language-independent named entity recognition. In: Proceedings NAACL-HLT Conference, pp. 142\u2013147 (2003)","DOI":"10.3115\/1119176.1119195"},{"key":"19_CR45","unstructured":"Wang, A., et al.: SuperGLUE: a stickier benchmark for general-purpose language understanding systems. In: Proceedings NeurIPS Conference, pp. 3266\u20133280 (2019)"},{"key":"19_CR46","unstructured":"Wang, J., Liang, Y., Meng, F., Li, Z., Qu, J., Zhou, J.: Cross-lingual summarization via chatgpt. arXiv e-prints, arXiv-2302 (2023)"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Wang, S., Scells, H., Koopman, B., Zuccon, G.: Can ChatGPT write a good Boolean query for systematic review literature search? arXiv e-prints, arXiv-2302 (2023)","DOI":"10.1145\/3539618.3591703"},{"key":"19_CR48","unstructured":"Wei, J., et al.: Chain of thought prompting elicits reasoning in large language models. arXiv preprint arXiv:2201.11903 (2022)"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Wu, T., Ribeiro, M.T., Heer, J., Weld, D.S.: Errudite: scalable, reproducible, and testable error analysis. In: Proceedings ACL Conference, pp. 747\u2013763 (2019)","DOI":"10.18653\/v1\/P19-1073"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Ye, X., Yavuz, S., Hashimoto, K., Zhou, Y., Xiong, C.: RNG-KBQA: generation augmented iterative ranking for knowledge base question answering. In: Proceedings ACL Conference, pp. 6032\u20136043 (2022)","DOI":"10.18653\/v1\/2022.acl-long.417"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Yih, W.T., Richardson, M., Meek, C., Chang, M.W., Suh, J.: The value of semantic parse labeling for knowledge base question answering. In: Proceedings ACL Conference, pp. 201\u2013206 (2016)","DOI":"10.18653\/v1\/P16-2033"},{"key":"19_CR52","unstructured":"Zhong, Q., Ding, L., Liu, J., Du, B., Tao, D.: Can ChatGPT understand too? A comparative study on ChatGPT and fine-tuned BERT. arXiv e-prints, arXiv-2302 (2023)"},{"key":"19_CR53","unstructured":"Zhu, K., et al.: PromptBench: towards evaluating the robustness of large language models on adversarial prompts. arXiv preprint arXiv:2306.04528 (2023)"},{"key":"19_CR54","unstructured":"Zhuo, T.Y., Huang, Y., Chen, C., Xing, Z.: Exploring AI ethics of ChatGPT: a diagnostic analysis. arXiv e-prints, arXiv-2301 (2023)"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web \u2013 ISWC 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-47240-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:24:54Z","timestamp":1730438694000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-47240-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031472398","9783031472404"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-47240-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISWC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Semantic Web Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2023","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":"semweb2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iswc2023.semanticweb.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"248","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"58","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}