{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T18:08:20Z","timestamp":1784138900736,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["No. 62376130"],"award-info":[{"award-number":["No. 62376130"]}]},{"name":"Program of New Twenty Policies for Universities of Jinan","award":["No.202333008"],"award-info":[{"award-number":["No.202333008"]}]},{"name":"Pilot Project for Integrated Innovation of Science, Education, Industry of Qilu University of Technology (Shandong Academy of Sciences)","award":["No.2025ZDZX01"],"award-info":[{"award-number":["No.2025ZDZX01"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809604","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"1834-1845","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["RES-MR: Risk-Aware Reasoning for Explainable and Safe Medication Recommendation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-2993-0248","authenticated-orcid":false,"given":"Cong","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5737-3594","authenticated-orcid":false,"given":"Jin","family":"Li","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1133-9379","authenticated-orcid":false,"given":"Shoujin","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0093-9854","authenticated-orcid":false,"given":"Yishuo","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6116-2524","authenticated-orcid":false,"given":"Huilin","family":"Gu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1840-3540","authenticated-orcid":false,"given":"Wenpeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences); Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00197"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3608857"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3488668"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1043"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-01960-3"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning. 7935-7952","author":"Chen Lichang","year":"2024","unstructured":"Lichang Chen, Chen Zhu, Jiuhai Chen, Davit Soselia, Tianyi Zhou, et al., 2024. ODIN: Disentangled reward mitigates hacking in RLHF. In Proceedings of the 41st International Conference on Machine Learning. 7935-7952."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709232"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25861"},{"key":"e_1_3_2_1_9_1","volume-title":"Zhenliang Zhang, and Furu Wei.","author":"Cheng Daixuan","year":"2025","unstructured":"Daixuan Cheng, Shaohan Huang, Xuekai Zhu, Bo Dai, Wayne Xin Zhao, Zhenliang Zhang, and Furu Wei. 2025. Reasoning with exploration: An entropy perspective. arXiv preprint arXiv:2506.14758 (2025), 1-19."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning. 1-21","author":"Chu Tianzhe","year":"2025","unstructured":"Tianzhe Chu, Yuexiang Zhai, Jihan Yang, Shengbang Tong, Saining Xie, Dale Schuurmans, Quoc V Le, Sergey Levine, and Yi Ma. 2025. SFT memorizes, RL generalizes: A comparative study of foundation model post-training. In Proceedings of the 42nd International Conference on Machine Learning. 1-21."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604915.3610646"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3559457"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 12th International Conference on Learning Representations. 1-14","author":"Dao Tri","year":"2024","unstructured":"Tri Dao. 2024. FlashAttention-2: Faster attention with better parallelism and work partitioning. In Proceedings of the 12th International Conference on Learning Representations. 1-14."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3645089"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 39th Annual Conference on Neural Information Processing Systems. 1-17","author":"Fan Chenxiao","year":"2025","unstructured":"Chenxiao Fan, Chongming Gao, Wentao Shi, Yaxin Gong, Zhao Zihao, et al., 2025. Fine-grained list-wise alignment for generative medication recommendation. In Proceedings of the 39th Annual Conference on Neural Information Processing Systems. 1-17."},{"key":"e_1_3_2_1_16_1","unstructured":"Yue Fang Yuxin Guo Jiaran Gao Hongxin Ding Xinke Jiang et al. 2025a. Toward better EHR reasoning in LLMs: Reinforcement learning with expert attention guidance. arXiv preprint arXiv:2508.13579 (2025) 1-18."},{"key":"e_1_3_2_1_17_1","unstructured":"Yi Fang Wenjie Wang Yang Zhang Fengbin Zhu Qifan Wang et al. 2025b. Reason4Rec: Large language models for recommendation with deliberative user preference alignment. arXiv preprint arXiv:2502.02061 (2025) 1-11."},{"key":"e_1_3_2_1_18_1","volume-title":"Enrique Lopez-Cuena, Adrian Tormos, et al.","author":"Garcia-Gasulla Dario","year":"2025","unstructured":"Dario Garcia-Gasulla, Jordi Bayarri-Planas, Ashwin Kumar Gururajan, Enrique Lopez-Cuena, Adrian Tormos, et al., 2025. The aloe family recipe for open and specialized healthcare LLMs. arXiv preprint arXiv:2505.04388 (2025), 1-82."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bdr.2020.100174"},{"key":"e_1_3_2_1_20_1","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang et al. 2025. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. arXiv preprint arXiv:2501.12948 (2025) 1-11."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761071"},{"key":"e_1_3_2_1_22_1","volume-title":"National Center for Health Statistics, and Commission on Professional and Hospital Activities","author":"Health Care Financing Administration","year":"1989","unstructured":"Health Care Financing Administration, National Center for Health Statistics, and Commission on Professional and Hospital Activities. 1989. The international classification of diseases, 9th revision, clinical modification: ICD-9-CM. Vol. 3. Commission on Professional and Hospital Activities."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 10th International Conference on Learning Representations. 1-20","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. LoRA: Low-rank adaptation of large language models. In Proceedings of the 10th International Conference on Learning Representations. 1-20."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3366349"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591672"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2109"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730055"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i11.33301"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28704"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 2nd International Conference on Learning Representations. 1-14","author":"Diederik","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In Proceedings of the 2nd International Conference on Learning Representations. 1-14."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2024.11437"},{"key":"e_1_3_2_1_34_1","volume-title":"Towards Fair Large Language Model-based Recommender Systems without Costly Retraining. arXiv preprint arXiv:2601.17492","author":"Li Jin","year":"2026","unstructured":"Jin Li, Huilin Gu, Shoujin Wang, Qi Zhang, Shui Yu, Chen Wang, Xiwei Xu, and Fang Chen. 2026. Towards Fair Large Language Model-based Recommender Systems without Costly Retraining. arXiv preprint arXiv:2601.17492 (2026)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-8183-9_29"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD61410.2024.10579995"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714533"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714727"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730161"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730211"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706631"},{"key":"e_1_3_2_1_42_1","unstructured":"Qidong Liu Xian Wu Xiangyu Zhao Yuanshao Zhu Zijian Zhang et al. 2024. Large language model distilling medication recommendation Model. arXiv preprint arXiv:2402.02803 (2024) 1-12."},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"Advancing chinese conversation-based patient guidance with a benchmark and knowledge-evolvable assistant","volume":"1","author":"Lu Wenpeng","year":"2025","unstructured":"Wenpeng Lu, Kangjun Liu, Jianlei Wang, Xueping Peng, Tao Shen, Fa Zhu, Weiyu Zhang, Jiabing Zhu, Tao Xin, and Athanasios V. Vasilakos. 2025b. Advancing chinese conversation-based patient guidance with a benchmark and knowledge-evolvable assistant. IEEE Journal of Biomedical and Health Informatics, Vol. 1, 1 (2025), 1-12.","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.3021188"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129021"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.22"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.856"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwac200"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/515"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3326929"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.178"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7881-7892","author":"Das Thibault","year":"2020","unstructured":"Sellam, Thibault and Das, Dipanjan and Parikh, Ankur. 2020. BLEURT: Learning robust metrics for text generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 7881-7892."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00762-z"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/825"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011126"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539089"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.780"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3694176"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-62008-0_20"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-021-00930-2"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1317"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671944"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/431"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkx1037"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/871"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad003"},{"key":"e_1_3_2_1_67_1","volume-title":"Rewarddance: Reward scaling in visual generation. arXiv preprint arXiv:2509.08826","author":"Wu Jie","year":"2025","unstructured":"Jie Wu, Yu Gao, Zilyu Ye, Ming Li, Liang Li, et al., 2025a. Rewarddance: Reward scaling in visual generation. arXiv preprint arXiv:2509.08826 (2025), 1-19."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103283"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557380"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511936"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Su Xian Monika E Grabowska Iftikhar J Kullo Yuan Luo Jordan W Smoller et al. 2025. Transformer patient embedding using electronic health records enables patient stratification and progression analysis. npj Digital Medicine Vol. 8 1 (2025) 521.","DOI":"10.1038\/s41746-025-01872-z"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"},{"key":"e_1_3_2_1_73_1","first-page":"1","article-title":"KELLM: Knowledge-enhanced label-wise large language model for safe and interpretable drug recommendation","volume":"14","author":"Xu Tianhan","year":"2025","unstructured":"Tianhan Xu and Bin Li. 2025. KELLM: Knowledge-enhanced label-wise large language model for safe and interpretable drug recommendation. Electronics, Vol. 14, 1 (2025), 1-23.","journal-title":"Electronics"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661370"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/513"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/514"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583872"},{"key":"e_1_3_2_1_78_1","volume-title":"DAPO: An open-source LLM reinforcement learning system at scale. arXiv preprint arXiv:2503.14476","author":"Yu Qiying","year":"2025","unstructured":"Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, et al., 2025. DAPO: An open-source LLM reinforcement learning system at scale. arXiv preprint arXiv:2503.14476 (2025), 1-16."},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1052"},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098109"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.1145\/3527662"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3437775"},{"key":"e_1_3_2_1_83_1","volume-title":"Fine-grained alignment of large language models for general medication recommendation without overprescription. arXiv preprint arXiv:2503.03687","author":"Zhao Zihao","year":"2025","unstructured":"Zihao Zhao, Chenxiao Fan, Chongming Gao, Fuli Feng, and Xiangnan He. 2025. Fine-grained alignment of large language models for general medication recommendation without overprescription. arXiv preprint arXiv:2503.03687 (2025), 1-17."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657785"},{"key":"e_1_3_2_1_85_1","unstructured":"Chujie Zheng Shixuan Liu Mingze Li Xiong-Hui Chen Bowen Yu et al. 2025. Group sequence policy optimization. arXiv preprint arXiv:2507.18071 (2025) 1-7."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511020"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:21:49Z","timestamp":1784136109000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":86,"alternative-id":["10.1145\/3805712.3809604","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809604","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}