{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T11:09:28Z","timestamp":1780916968818,"version":"3.54.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819214648","type":"print"},{"value":"9789819214655","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\/978-981-92-1465-5_39","type":"book-chapter","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:25:01Z","timestamp":1780914301000},"page":"497-509","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Harnessing the\u00a0Power of\u00a0Reinforcement Learning for\u00a0Language-Model-Based Information Retriever via\u00a0Query-Document Co-Augmentation"],"prefix":"10.1007","author":[{"given":"Jingming","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yumeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao-Xiang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"39_CR1","unstructured":"Asai, A., Wu, Z., Wang, Y., Sil, A., Hajishirzi, H.: Self-rag: Learning to retrieve, generate, and critique through self-reflection. In: The Twelfth International Conference on Learning Representations (2024). https:\/\/openreview.net\/forum?id=hSyW5go0v8"},{"key":"39_CR2","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B.: Modern information retrieval, vol. 463, ACM Press New York (1999)"},{"key":"39_CR3","unstructured":"Christiano, P.F., Leike, J., Brown, T.B., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. ArXiv abs\/1706.03741 (2017). https:\/\/api.semanticscholar.org\/CorpusID:4787508"},{"key":"39_CR4","doi-asserted-by":"crossref","unstructured":"Dageville, B., et al.: The snowflake elastic data warehouse. In: Proceedings of the 2016 International Conference on Management of Data, pp. 215\u2013226 (2016)","DOI":"10.1145\/2882903.2903741"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Dai, S., et al.: Cocktail: a comprehensive information retrieval benchmark with LLM-generated documents integration (2024). https:\/\/arxiv.org\/abs\/2405.16546","DOI":"10.18653\/v1\/2024.findings-acl.421"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Dalton, J., Dietz, L., Allan, J.: Entity query feature expansion using knowledge base links. In: Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval (2014). https:\/\/api.semanticscholar.org\/CorpusID:12620927","DOI":"10.1145\/2600428.2609628"},{"key":"39_CR7","unstructured":"Gao, Y., et al.: Retrieval-augmented generation for large language models: a survey 2, 1. arXiv preprint arXiv:2312.10997 (2023)"},{"key":"39_CR8","unstructured":"Guo, D., et al.: Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)"},{"key":"39_CR9","unstructured":"Hsu, S., Khattab, O., Finn, C., Sharma, A.: Grounding by trying: LLMs with reinforcement learning-enhanced retrieval arXiv preprint arXiv:2410.23214 (2024)"},{"key":"39_CR10","unstructured":"Hu, J.: Reinforce++: a simple and efficient approach for aligning large language models. ArXiv abs\/2501.03262 (2025). https:\/\/api.semanticscholar.org\/CorpusID:275342265"},{"key":"39_CR11","unstructured":"Hu, J.: Reinforce++: a simple and efficient approach for aligning large language models. arXiv preprint arXiv:2501.03262 (2025)"},{"issue":"4","key":"39_CR12","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., Kek\u00e4l\u00e4inen, J.: Cumulated gain-based evaluation of IR techniques. ACM Trans. Inf. Syst. (TOIS) 20(4), 422\u2013446 (2002)","journal-title":"ACM Trans. Inf. Syst. (TOIS)"},{"key":"39_CR13","unstructured":"Jiang, P., et al.: Deepretrieval: hacking real search engines and retrievers with large language models via reinforcement learning arXiv preprint arXiv:2503.00223 (2025)"},{"key":"39_CR14","doi-asserted-by":"publisher","unstructured":"Karpukhin, V., et al.: Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6769\u20136781. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.550, https:\/\/aclanthology.org\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"39_CR15","doi-asserted-by":"crossref","unstructured":"Lee, H., Kedia, A., Lee, J., Paranjape, A., Manning, C., Woo, K.G.: You only need one model for open-domain question answering. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 3047\u20133060. Association for Computational Linguistics, Abu Dhabi, United Arab Emirates (2022). https:\/\/aclanthology.org\/2022.emnlp-main.198","DOI":"10.18653\/v1\/2022.emnlp-main.198"},{"key":"39_CR16","unstructured":"Liu, Z., et al.: Understanding r1-zero-like training: a critical perspective. arXiv preprint arXiv:2503.20783 (2025)"},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Ma, X., Gong, Y., He, P., Zhao, H., Duan, N.: Query rewriting for retrieval-augmented large language models (2023). https:\/\/arxiv.org\/abs\/2305.14283","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Ma, X., Gong, Y., He, P., Zhao, H., Duan, N.: Query rewriting in retrieval-augmented large language models. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 5303\u20135315 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.322"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Meij, E., Trieschnigg, D., de Rijke, M., Kraaij, W.: Conceptual language models for domain-specific retrieval. Inf. Process. Manag. 46, 448\u2013469 (2010). https:\/\/api.semanticscholar.org\/CorpusID:10929365","DOI":"10.1016\/j.ipm.2009.09.005"},{"key":"39_CR20","doi-asserted-by":"crossref","unstructured":"Metzler, D., Croft, W.B.: Latent concept expansion using markov random fields. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 311\u2013318 (2007)","DOI":"10.1145\/1277741.1277796"},{"key":"39_CR21","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. ArXiv abs\/2203.02155 (2022). https:\/\/api.semanticscholar.org\/CorpusID:246426909"},{"key":"39_CR22","unstructured":"Yang, A., et al.: Qwen2.5 technical report (2025). https:\/\/arxiv.org\/abs\/2412.15115"},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Robertson, S., Zaragoza, H.: The probabilistic relevance framework: Bm25 and beyond. Found. Trends\u00ae Inf. Retrieval 3(4), 333\u2013389 (2009)","DOI":"10.1561\/1500000019"},{"issue":"5","key":"39_CR24","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G Salton","year":"1988","unstructured":"Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513\u2013523 (1988)","journal-title":"Inf. Process. Manag."},{"key":"39_CR25","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. ArXiv abs\/1707.06347 (2017). https:\/\/api.semanticscholar.org\/CorpusID:28695052"},{"key":"39_CR26","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":"39_CR27","doi-asserted-by":"crossref","unstructured":"Trivedi, H., Balasubramanian, N., Khot, T., Sabharwal, A.: Interleaving retrieval with chain-of-thought reasoning for knowledge-intensive multi-step questions (2023). https:\/\/arxiv.org\/abs\/2212.10509","DOI":"10.18653\/v1\/2023.acl-long.557"},{"key":"39_CR28","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":"39_CR29","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., Nie, J.Y.: C-pack: packed resources for general chinese embeddings. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 641\u2013649 (2024)","DOI":"10.1145\/3626772.3657878"},{"key":"39_CR30","unstructured":"Xu, Z., et al.: Rethinking on-policy optimization for query augmentation arXiv preprint arXiv:2510.17139 (2025)"},{"key":"39_CR31","unstructured":"Yao, S., et al.: React: synergizing reasoning and acting in language models (2023). https:\/\/arxiv.org\/abs\/2210.03629"},{"key":"39_CR32","unstructured":"Zhao, S., Yang, Y., Wang, Z., He, Z., Qiu, L.K., Qiu, L.: Retrieval augmented generation (rag) and beyond: a comprehensive survey on how to make your LLMs use external data more wisely. ArXiv abs\/2409.14924 (2024). https:\/\/api.semanticscholar.org\/CorpusID:272827955"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-1465-5_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T10:25:27Z","timestamp":1780914327000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-1465-5_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819214648","9789819214655"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-1465-5_39","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":"9 June 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"We develop an LLM-based retriever that jointly augments both queries and documents, and design a bidirectional RL framework to optimize these augmentation policies collaboratively. We utilize LLMs to help proofread the manuscript and fix writing issues.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"The Use of Large Language Models"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hong Kong","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":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pakdd2026.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}