{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:53:51Z","timestamp":1759334031494,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032061089"},{"type":"electronic","value":"9783032061096"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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\/978-3-032-06109-6_24","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T10:05:00Z","timestamp":1759226700000},"page":"419-436","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FinCPRG: A Bidirectional Generation Pipeline for\u00a0Hierarchical Queries and\u00a0Rich Relevance in\u00a0Financial Chinese Passage Retrieval"],"prefix":"10.1007","author":[{"given":"Xuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Beilin","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qinhong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixiao","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fufang","family":"Wen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binjie","family":"Fei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongliang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linna","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"24_CR1","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":"24_CR2","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: FinTextQA: a dataset for long-form financial question answering. 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), Bangkok, Thailand, pp. 6025\u20136047. Association for Computational Linguistics (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.328","DOI":"10.18653\/v1\/2024.acl-long.328"},{"key":"24_CR3","unstructured":"Chen, J., et al.: Air-bench: Automated heterogeneous information retrieval benchmark (2024). https:\/\/arxiv.org\/abs\/2412.13102"},{"key":"24_CR4","doi-asserted-by":"publisher","unstructured":"Dai, S., et al.: Cocktail: a comprehensive information retrieval benchmark with LLM-generated documents integration. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Findings of the Association for Computational Linguistics: ACL 2024, Bangkok, Thailand, pp. 7052\u20137074. Association for Computational Linguistics (2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-acl.421","DOI":"10.18653\/v1\/2024.findings-acl.421"},{"key":"24_CR5","doi-asserted-by":"publisher","unstructured":"Gao, L., Ma, X., Lin, J., Callan, J.: Precise zero-shot dense retrieval without relevance labels. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, Canada, pp. 1762\u20131777. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.99","DOI":"10.18653\/v1\/2023.acl-long.99"},{"key":"24_CR6","unstructured":"Jeronymo, V., et al.: Inpars-v2: large language models as efficient dataset generators for information retrieval. arXiv preprint arXiv:2301.01820 (2023)"},{"key":"24_CR7","unstructured":"Kazemi, S.M., et al.: Time2vec: learning a vector representation of time. In: NeurIPS (2019)"},{"key":"24_CR8","doi-asserted-by":"publisher","unstructured":"Muennighoff, N., Tazi, N., Magne, L., Reimers, N.: MTEB: Massive text embedding benchmark. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, pp. 2014\u20132037. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.148, https:\/\/aclanthology.org\/2023.eacl-main.148\/","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"24_CR9","doi-asserted-by":"publisher","unstructured":"Qiu, Y., et al.: DuReader-retrieval: a large-scale Chinese benchmark for passage retrieval from web search engine. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates, pp. 5326\u20135338. Association for Computational Linguistics (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.357","DOI":"10.18653\/v1\/2022.emnlp-main.357"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Rahmani, H.A., Craswell, N., Yilmaz, E., Mitra, B., Campos, D.: Synthetic test collections for retrieval evaluation. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2647\u20132651 (2024)","DOI":"10.1145\/3626772.3657942"},{"key":"24_CR11","doi-asserted-by":"publisher","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. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.naacl-main.185","DOI":"10.18653\/v1\/2021.naacl-main.185"},{"key":"24_CR12","unstructured":"Tang, Y., Yang, Y.: Finmteb: finance massive text embedding benchmark (2025). https:\/\/arxiv.org\/abs\/2502.10990"},{"key":"24_CR13","unstructured":"Team, C.L.: Chuxin-embedding: a Chinese text retrieval enhancement embedding model (2024). https:\/\/github.com\/chuxin-llm\/Chuxin-Embedding. accessed: 2024-03"},{"key":"24_CR14","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: Beir: a heterogeneous benchmark for zero-shot evaluation of information retrieval models. In: Vanschoren, J., Yeung, S. (eds.) Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, vol.\u00a01 (2021)"},{"key":"24_CR15","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-031-68309-1_1","volume-title":"DEXA 2024","author":"J Wang","year":"2024","unstructured":"Wang, J., et al.: CSPRD: a financial policy retrieval dataset for Chinese stock market. In: Strauss, C., Amagasa, T., Manco, G., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) DEXA 2024. LNCS, vol. 14910, pp. 3\u201317. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-68309-1_1"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Wang, K., Thakur, N., Reimers, N., Gurevych, I.: GPL: generative pseudo labeling for unsupervised domain adaptation of dense retrieval. arXiv preprint arXiv:2112.07577 (2021)","DOI":"10.18653\/v1\/2022.naacl-main.168"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., Wei, F.: Improving text embeddings with 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), Bangkok, Thailand, pp. 11897\u201311916. Association for Computational Linguistics (2024). https:\/\/aclanthology.org\/2024.acl-long.642\/","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Wang, L., Yang, N., Wei, F.: Query2doc: query expansion with large language models. arXiv preprint arXiv:2303.07678 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.585"},{"key":"24_CR19","unstructured":"Weller, O., et al.: When do generative query and document expansions fail? a comprehensive study across methods, retrievers, and datasets. In: Findings of the Association for Computational Linguistics: EACL 2024, St. Julian\u2019s, Malta, pp. 1987\u20132003. Association for Computational Linguistics (2024). https:\/\/aclanthology.org\/2024.findings-eacl.134"},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Xie, X., et al.: T2ranking: a large-scale Chinese benchmark for passage ranking. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR \u201923, New York, NY, USA, pp. 2681\u20132690. Association for Computing Machinery (2023). https:\/\/doi.org\/10.1145\/3539618.3591874","DOI":"10.1145\/3539618.3591874"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Xu, X., et al.: Finbert2: a specialized bidirectional encoder for bridging the gap in finance-specific deployment of large language models. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM (2025). https:\/\/doi.org\/10.1145\/3711896.3737219","DOI":"10.1145\/3711896.3737219"},{"key":"24_CR22","doi-asserted-by":"publisher","unstructured":"Zhang, J., Lan, Z., He, J.: Contrastive learning of sentence embeddings from scratch. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, pp. 3916\u20133932. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.238","DOI":"10.18653\/v1\/2023.emnlp-main.238"}],"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\/978-3-032-06109-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T10:05:17Z","timestamp":1759226717000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06109-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783032061089","9783032061096"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06109-6_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","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":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","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":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}