{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:25:29Z","timestamp":1772119529019,"version":"3.50.1"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031434143","type":"print"},{"value":"9783031434150","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\/978-3-031-43415-0_31","type":"book-chapter","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:01:51Z","timestamp":1694851311000},"page":"525-542","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for\u00a0Knowledge-Grounded Dialogue Generation"],"prefix":"10.1007","author":[{"given":"Jiaqi","family":"Bai","sequence":"first","affiliation":[]},{"given":"Zhao","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Ze","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Xinnian","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Hongcheng","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Zhoujun","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,9,17]]},"reference":[{"key":"31_CR1","doi-asserted-by":"publisher","unstructured":"Bao, S., et al.: PLATO-2: Towards building an open-domain chatbot via curriculum learning. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 2513\u20132525. Association for Computational Linguistics, Online (Aug 2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.222","DOI":"10.18653\/v1\/2021.findings-acl.222"},{"key":"31_CR2","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":"31_CR3","doi-asserted-by":"crossref","unstructured":"Cui, L., Cheng, S., Wu, Y., Zhang, Y.: On commonsense cues in bert for solving commonsense tasks. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 683\u2013693 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.61"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Cui, L., Wu, Y., Liu, S., Zhang, Y.: Knowledge enhanced fine-tuning for better handling unseen entities in dialogue generation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 2328\u20132337 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.179"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Davison, J., Feldman, J., Rush, A.M.: Commonsense knowledge mining from pretrained models. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 1173\u20131178 (2019)","DOI":"10.18653\/v1\/D19-1109"},{"key":"31_CR6","unstructured":"Dinan, E., Roller, S., Shuster, K., Fan, A., Auli, M., Weston, J.: Wizard of wikipedia: Knowledge-powered conversational agents. In: International Conference on Learning Representations (2018)"},{"issue":"5","key":"31_CR7","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"JL Fleiss","year":"1971","unstructured":"Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378 (1971)","journal-title":"Psychol. Bull."},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Ghazvininejad, M., et al.: A knowledge-grounded neural conversation model. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11977"},{"key":"31_CR9","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: International Conference on Machine Learning, pp. 3929\u20133938. PMLR (2020)"},{"key":"31_CR10","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration. In: International Conference on Learning Representations (2019)"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Huang, X., He, H., Bao, S., Wang, F., Wu, H., Wang, H.: Plato-kag: Unsupervised knowledge-grounded conversation via joint modeling. In: Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI, pp. 143\u2013154 (2021)","DOI":"10.18653\/v1\/2021.nlp4convai-1.14"},{"key":"31_CR12","doi-asserted-by":"publisher","unstructured":"Karimi Mahabadi, R., et al.: Prompt-free and efficient few-shot learning with language models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3638\u20133652. Association for Computational Linguistics, Dublin, Ireland (May 2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.254","DOI":"10.18653\/v1\/2022.acl-long.254"},{"key":"31_CR13","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171\u20134186 (2019)"},{"key":"31_CR14","unstructured":"Kim, B., Ahn, J., Kim, G.: Sequential latent knowledge selection for knowledge-grounded dialogue. In: International Conference on Learning Representations (2019)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Komeili, M., Shuster, K., Weston, J.: Internet-augmented dialogue generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 8460\u20138478 (2022)","DOI":"10.18653\/v1\/2022.acl-long.579"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7871\u20137880 (2020)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"31_CR18","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive nlp tasks: Adv. Neural. Inf. Process. Syst. 33, 9459\u20139474 (2020)"},{"key":"31_CR19","first-page":"8475","volume":"33","author":"L Li","year":"2020","unstructured":"Li, L., Xu, C., Wu, W., Zhao, Y., Zhao, X., Tao, C.: Zero-resource knowledge-grounded dialogue generation. Adv. Neural. Inf. Process. Syst. 33, 8475\u20138485 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR20","doi-asserted-by":"publisher","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 4582\u20134597. Association for Computational Linguistics, Online (Aug 2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.353","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhao, J., Lyu, M.R., Wang, L.: Eliciting knowledge from large pre-trained models for unsupervised knowledge-grounded conversation. arXiv preprint arXiv:2211.01587 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.721"},{"key":"31_CR22","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: Knowledge-grounded dialogue generation with a unified knowledge representation. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 206\u2013218. Association for Computational Linguistics, Seattle, United States (Jul 2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.15","DOI":"10.18653\/v1\/2022.naacl-main.15"},{"key":"31_CR23","doi-asserted-by":"crossref","unstructured":"Lian, R., Xie, M., Wang, F., Peng, J., Wu, H.: Learning to select knowledge for response generation in dialog systems. In: IJCAI International Joint Conference on Artificial Intelligence, p. 5081 (2019)","DOI":"10.24963\/ijcai.2019\/706"},{"key":"31_CR24","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1162\/tacl\\_a_00343","volume":"8","author":"Y Liu","year":"2020","unstructured":"Liu, Y., et al.: Multilingual denoising pre-training for neural machine translation. Trans. Assoc. Comput. Linguist. 8, 726\u2013742 (2020). https:\/\/doi.org\/10.1162\/tacl_a_00343","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"31_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Multi-stage prompting for knowledgeable dialogue generation. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 1317\u20131337 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.104"},{"key":"31_CR26","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam (2018)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Meng, C., et al.: Dukenet: A dual knowledge interaction network for knowledge-grounded conversation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval pp. 1151\u20131160 (2020)","DOI":"10.1145\/3397271.3401097"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Petroni, F., et al.: Language models as knowledge bases? In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 2463\u20132473 (2019)","DOI":"10.18653\/v1\/D19-1250"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Prabhumoye, S., Hashimoto, K., Zhou, Y., Black, A.W., Salakhutdinov, R.: Focused attention improves document-grounded generation. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4274\u20134287 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.338"},{"key":"31_CR30","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog (2019)"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Roller, S., et al.: Recipes for building an open-domain chatbot. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 300\u2013325 (2021)","DOI":"10.18653\/v1\/2021.eacl-main.24"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Schick, T., Sch\u00fctze, H.: It\u2019s not just size that matters: Small language models are also few-shot learners. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2339\u20132352 (2021)","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"31_CR33","doi-asserted-by":"crossref","unstructured":"Shin, T., Razeghi, Y., Logan IV, R.L., Wallace, E., Singh, S.: Autoprompt: Eliciting knowledge from language models with automatically generated prompts. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4222\u20134235 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 3784\u20133803 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.320"},{"key":"31_CR35","doi-asserted-by":"publisher","unstructured":"Sun, Q., et al.: Multimodal dialogue response generation. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2854\u20132866. Association for Computational Linguistics, Dublin, Ireland (May 2022). https:\/\/doi.org\/10.18653\/v1\/2022.acl-long.204","DOI":"10.18653\/v1\/2022.acl-long.204"},{"key":"31_CR36","doi-asserted-by":"publisher","unstructured":"Sun, Q., et al.: Stylized knowledge-grounded dialogue generation via disentangled template rewriting. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 3304\u20133318. Association for Computational Linguistics, Seattle, United States (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.241","DOI":"10.18653\/v1\/2022.naacl-main.241"},{"key":"31_CR37","unstructured":"Sun, W., Shi, Z., Gao, S., Ren, P., de Rijke, M., Ren, Z.: Contrastive learning reduces hallucination in conversations. CoRR abs\/2212.10400 (2022). arXiv:2212.10400"},{"key":"31_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inform. Process. Syst. 30 (2017)"},{"key":"31_CR39","doi-asserted-by":"crossref","unstructured":"Wang, C., Liu, P., Zhang, Y.: Can generative pre-trained language models serve as knowledge bases for closed-book qa? In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 3241\u20133251 (2021)","DOI":"10.18653\/v1\/2021.acl-long.251"},{"key":"31_CR40","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Retrieval-free knowledge-grounded dialogue response generation with adapters. In: Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pp. 93\u2013107 (2022)","DOI":"10.18653\/v1\/2022.dialdoc-1.10"},{"key":"31_CR41","doi-asserted-by":"publisher","unstructured":"Zhao, L., et al.: Domain-oriented prefix-tuning: Towards efficient and generalizable fine-tuning for zero-shot dialogue summarization. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4848\u20134862. Association for Computational Linguistics, Seattle, United States (Jul 2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.357","DOI":"10.18653\/v1\/2022.naacl-main.357"},{"key":"31_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, T., Zhao, R., Eskenazi, M.: Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 654\u2013664 (2017)","DOI":"10.18653\/v1\/P17-1061"},{"key":"31_CR43","doi-asserted-by":"publisher","unstructured":"Zhao, X., Fu, T., Tao, C., Wu, W., Zhao, D., Yan, R.: Learning to express in knowledge-grounded conversation. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2258\u20132273. Association for Computational Linguistics, Seattle, United States (Jul 2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.164","DOI":"10.18653\/v1\/2022.naacl-main.164"},{"key":"31_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, X., Wu, W., Xu, C., Tao, C., Zhao, D., Yan, R.: Knowledge-grounded dialogue generation with pre-trained language models. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3377\u20133390 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.272"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Zhou, K., Prabhumoye, S., Black, A.W.: A dataset for document grounded conversations. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 708\u2013713 (2018)","DOI":"10.18653\/v1\/D18-1076"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, X., Zhang, Y., Cui, L., Huang, D.: Evaluating commonsense in pre-trained language models. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol. 34, pp. 9733\u20139740 (2020)","DOI":"10.1609\/aaai.v34i05.6523"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases: Research Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43415-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T08:09:50Z","timestamp":1694851790000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43415-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031434143","9783031434150"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43415-0_31","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":"17 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"18 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.ecmlpkdd.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"829","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":"196","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":"24% - 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":"3.63","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":"4.5","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)"}},{"value":"Applied Data Science Track: 239 submissions, 58 accepted papers; Demo Track: 31 submissions, 16 accepted papers.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}