{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T21:14:55Z","timestamp":1773177295948,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556366","type":"print"},{"value":"9789819556373","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-5637-3_4","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:55:45Z","timestamp":1767318945000},"page":"49-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Comparative Study of\u00a0Specialized LLMs as\u00a0Dense Retrievers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1144-1298","authenticated-orcid":false,"given":"Hengran","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-4999","authenticated-orcid":false,"given":"Keping","family":"Bi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-8674","authenticated-orcid":false,"given":"Jiafeng","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"4_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"4_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"4_CR3","unstructured":"Bai, S., Chen, K., Liu, X., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"4_CR4","unstructured":"BehnamGhader, P., Adlakha, V., Mosbach, M., Bahdanau, D., Chapados, N., Reddy, S.: Llm2vec: large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961 (2024)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Boteva, V., Gholipour, D., Sokolov, A., Riezler, S.: A full-text learning to rank dataset for medical information retrieval. In: Advances in Information Retrieval: 38th European Conference on IR Research, pp. 716\u2013722. Springer (2016)","DOI":"10.1007\/978-3-319-30671-1_58"},{"key":"4_CR6","unstructured":"Chang, W.C., Yu, F.X., Chang, Y.W., Yang, Y., Kumar, S.: Pre-training tasks for embedding-based large-scale retrieval. arXiv preprint arXiv:2002.03932 (2020)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Cohan, A., Feldman, S., Beltagy, I., Downey, D., Weld, D.S.: Specter: document-level representation learning using citation-informed transformers. arXiv preprint arXiv:2004.07180 (2020)","DOI":"10.18653\/v1\/2020.acl-main.207"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Craswell, N., Mitra, B., Yilmaz, E., Campos, D., Voorhees, E.M.: Overview of the trec 2019 deep learning track. arXiv preprint arXiv:2003.07820 (2020)","DOI":"10.6028\/NIST.SP.1266.deep-overview"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Gao, L., Callan, J.: Unsupervised corpus aware language model pre-training for dense passage retrieval. arXiv preprint arXiv:2108.05540 (2021)","DOI":"10.18653\/v1\/2022.acl-long.203"},{"key":"4_CR10","unstructured":"Guo, D., Yang, D., Zhang, H., Song, J., et\u00a0al.: Deepseek-r1: incentivizing reasoning capability in LLMS via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"issue":"4","key":"4_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3486250","volume":"40","author":"J Guo","year":"2022","unstructured":"Guo, J., Cai, Y., Fan, Y., Sun, F., Zhang, R., Cheng, X.: Semantic models for the first-stage retrieval: a comprehensive review. ACM Trans. Inf. Syst. (TOIS) 40(4), 1\u201342 (2022)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Guo, J., Fan, Y., Ai, Q., Croft, W.B.: A deep relevance matching model for ad-hoc retrieval. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, pp. 55\u201364 (2016)","DOI":"10.1145\/2983323.2983769"},{"key":"4_CR13","unstructured":"Hendrycks, D., Basart, S., Kadavath, S., Mazeika, M., et\u00a0al.: Measuring coding challenge competence with apps. arXiv preprint arXiv:2105.09938 (2021)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Huang, J., Tang, D., Shou, L., et\u00a0al.: Cosqa: 20,000+ web queries for code search and question answering. arXiv preprint arXiv:2105.13239 (2021)","DOI":"10.18653\/v1\/2021.acl-long.442"},{"key":"4_CR15","unstructured":"Hui, B., Yang, J., Cui, Z., et\u00a0al.: Qwen2. 5-coder technical report. arXiv preprint arXiv:2409.12186 (2024)"},{"key":"4_CR16","unstructured":"Husain, H., Wu, H.H., Gazit, T., Allamanis, M., Brockschmidt, M.: Codesearchnet challenge: evaluating the state of semantic code search. arXiv preprint arXiv:1909.09436 (2019)"},{"key":"4_CR17","doi-asserted-by":"crossref","unstructured":"Karpukhin, V., Oguz, B., Min, S., Lewis, P.S., et\u00a0al.: Dense passage retrieval for open-domain question answering. In: EMNLP (1), pp. 6769\u20136781 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Li, C., Liu, Z., Xiao, S., Shao, Y., Lian, D.: Llama2vec: unsupervised adaptation of large language models for dense retrieval. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 3490\u20133500 (2024)","DOI":"10.18653\/v1\/2024.acl-long.191"},{"key":"4_CR19","unstructured":"Li, X., Dong, K., Lee, Y.Q., Xia, W., et\u00a0al.: Coir: a comprehensive benchmark for code information retrieval models. arXiv preprint arXiv:2407.02883 (2024)"},{"key":"4_CR20","unstructured":"Liu, A., Feng, B., Xue, B., et\u00a0al.: Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)"},{"key":"4_CR21","doi-asserted-by":"crossref","unstructured":"Ma, X., Guo, J., Zhang, R., Fan, Y., Ji, X., Cheng, X.: Prop: pre-training with representative words prediction for ad-hoc retrieval. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp. 283\u2013291 (2021)","DOI":"10.1145\/3437963.3441777"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, L., Yang, N., Wei, F., Lin, J.: Fine-tuning llama for multi-stage text retrieval. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2421\u20132425 (2024)","DOI":"10.1145\/3626772.3657951"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Maia, M., Handschuh, S., Freitas, A., Davis, B., et\u00a0al.: Www\u201918 open challenge: financial opinion mining and question answering. In: Companion Proceedings of the Web Conference 2018, pp. 1941\u20131942 (2018)","DOI":"10.1145\/3184558.3192301"},{"key":"4_CR24","unstructured":"Nguyen, T., Rosenberg, M., Song, X., Gao, J., Tiwary, S., Majumder, R., Deng, L.: Ms marco: a human-generated machine reading comprehension dataset (2016)"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Qu, Y., Ding, Y., Liu, J., Liu, K., et\u00a0al.: Rocketqa: an optimized training approach to dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2010.08191 (2020)","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Robertson, S., Zaragoza, H., et\u00a0al.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends\u00ae Inf. Retrieval 3(4), 333\u2013389 (2009)","DOI":"10.1561\/1500000019"},{"key":"4_CR27","unstructured":"Springer, J.M., Kotha, S., Fried, D., Neubig, G., Raghunathan, A.: Repetition improves language model embeddings. arXiv preprint arXiv:2402.15449 (2024)"},{"key":"4_CR28","unstructured":"Springer, J.M., Kotha, S., Fried, D., Neubig, G., Raghunathan, A.: Repetition improves language model embeddings. arXiv preprint arXiv:2402.15449 (2024)"},{"key":"4_CR29","unstructured":"Thakur, N., Reimers, N., R\u00fcckl\u00e9, A., Srivastava, A., Gurevych, I.: Beir: a heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)"},{"key":"4_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Wachsmuth, H., Syed, S., Stein, B.: Retrieval of the best counterargument without prior topic knowledge. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 241\u2013251 (2018)","DOI":"10.18653\/v1\/P18-1023"},{"key":"4_CR32","unstructured":"Wang, L.L., Lo, K., Chandrasekhar, Y., Reas, R., et\u00a0al.: Cord-19: the covid-19 open research dataset. ArXiv pp. arXiv\u20132004 (2020)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Shao, Y., Cao, Z.: Retromae: pre-training retrieval-oriented language models via masked auto-encoder. arXiv preprint arXiv:2205.12035 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.35"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Yan, W., Tian, Y., Li, Y., et\u00a0al.: Codetransocean: a comprehensive multilingual benchmark for code translation. arXiv preprint arXiv:2310.04951 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.337"},{"key":"4_CR35","unstructured":"Yang, A., Yang, B., Hui, B., et\u00a0al.: Qwen2 technical report (2024)"},{"key":"4_CR36","unstructured":"Yang, A., Yang, B., Zhang, B., et\u00a0al.: Qwen2.5 technical report (2025)"},{"key":"4_CR37","unstructured":"Yang, A., Zhang, B., Hui, B., et\u00a0al.: Qwen2. 5-math technical report: Toward mathematical expert model via self-improvement. arXiv preprint arXiv:2409.12122 (2024)"},{"key":"4_CR38","unstructured":"Zhang, H., et al.: Unleashing the power of LLMS in dense retrieval with query likelihood modeling. arXiv preprint arXiv:2504.05216 (2025)"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Zheng, T., Zhang, G., Shen, T., et\u00a0al.: Opencodeinterpreter: integrating code generation with execution and refinement. arXiv preprint arXiv:2402.14658 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.762"},{"key":"4_CR40","doi-asserted-by":"crossref","unstructured":"Zhuang, S., Ma, X., Koopman, B., Lin, J., Zuccon, G.: Promptreps: prompting large language models to generate dense and sparse representations for zero-shot document retrieval. arXiv preprint arXiv:2404.18424 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.250"}],"container-title":["Lecture Notes in Computer Science","Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5637-3_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T01:55:47Z","timestamp":1767318947000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5637-3_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556366","9789819556373"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5637-3_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CCIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shihezi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccir2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cips-ir.org.cn\/CCIR2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}