{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:10:42Z","timestamp":1775913042866,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"SIRG - CityU Strategic Interdisciplinary Research Grant","award":["No.7020046, No.7020074"],"award-info":[{"award-number":["No.7020046, No.7020074"]}]},{"name":"CCF-Tencent Open Fund"},{"name":"CityU - HKIDS Early Career Research Grant","award":["No.9360163"],"award-info":[{"award-number":["No.9360163"]}]},{"name":"APRC - CityU New Research Initiatives","award":["No.9610565, Start-up Grant for New Faculty of CityU"],"award-info":[{"award-number":["No.9610565, Start-up Grant for New Faculty of CityU"]}]},{"name":"Hong Kong Environmental and Conservation Fund","award":["No. 88\/2022"],"award-info":[{"award-number":["No. 88\/2022"]}]},{"name":"Research Impact Fund","award":["No.R1015-23"],"award-info":[{"award-number":["No.R1015-23"]}]},{"name":"Hong Kong ITC Innovation and Technology Fund Midstream Research Programme for Universities Project","award":["No.ITS\/034\/22MS"],"award-info":[{"award-number":["No.ITS\/034\/22MS"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3657722","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"1104-1114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":65,"title":["When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0751-2602","authenticated-orcid":false,"given":"Qidong","family":"Liu","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1118-9710","authenticated-orcid":false,"given":"Xian","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Jarvis Research Center, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2926-4416","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"City University of Hong Kong, Hong Kong, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5657-181X","authenticated-orcid":false,"given":"Yuanshao","family":"Zhu","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3971-9907","authenticated-orcid":false,"given":"Derong","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7888-0587","authenticated-orcid":false,"given":"Feng","family":"Tian","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2195-2847","authenticated-orcid":false,"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Tencent YouTu Lab, Jarvis Research Center, Shenzhen, China"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.446"},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_4_1","first-page":"1","article-title":"Preliminary study on the construction of Chinese medical knowledge graph","volume":"33","author":"Byambasuren Odma","year":"2019","unstructured":"Odma Byambasuren, Yunfei Yang, Zhifang Sui, Damai Dai, Baobao Chang, Sujian Li, and Hongying Zan. 2019. Preliminary study on the construction of Chinese medical knowledge graph. Journal of Chinese Information Processing 33, 10 (2019), 1--9.","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_3_2_1_5_1","volume-title":"Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796","author":"Crawshaw Michael","year":"2020","unstructured":"Michael Crawshaw. 2020. Multi-task learning with deep neural networks: A survey. arXiv preprint arXiv:2009.09796 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"A survey for in-context learning. arXiv preprint arXiv:2301.00234","author":"Dong Qingxiu","year":"2022","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2022. A survey for in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_1_8_1","unstructured":"Wenqi Fan Xiangyu Zhao Xiao Chen Jingran Su Jingtong Gao Lin Wang Qidong Liu Yiqi Wang Han Xu Lei Chen et al. 2022. A comprehensive survey on trustworthy recommender systems. arXiv preprint arXiv:2209.10117 (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046","author":"Fan Wenqi","year":"2023","unstructured":"Wenqi Fan, Zihuai Zhao, Jiatong Li, Yunqing Liu, Xiaowei Mei, Yiqi Wang, Jiliang Tang, and Qing Li. 2023. Recommender systems in the era of large language models (llms). arXiv preprint arXiv:2307.02046 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"A Unified Framework for Multi-Domain CTR Prediction via Large Language Models. arXiv preprint arXiv:2312.10743","author":"Fu Zichuan","year":"2023","unstructured":"Zichuan Fu, Xiangyang Li, Chuhan Wu, Yichao Wang, Kuicai Dong, Xiangyu Zhao, Mengchen Zhao, Huifeng Guo, and Ruiming Tang. 2023. A Unified Framework for Multi-Domain CTR Prediction via Large Language Models. arXiv preprint arXiv:2312.10743 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Sparsely activated mixture-of-experts are robust multi-task learners. arXiv preprint arXiv:2204.07689","author":"Gupta Shashank","year":"2022","unstructured":"Shashank Gupta, Subhabrata Mukherjee, Krishan Subudhi, Eduardo Gonzalez, Damien Jose, Ahmed H Awadallah, and Jianfeng Gao. 2022. Sparsely activated mixture-of-experts are robust multi-task learners. arXiv preprint arXiv:2204.07689 (2022)."},{"key":"e_1_3_2_1_12_1","volume-title":"A survey on large language models: Applications, challenges, limitations, and practical usage. TechRxiv","author":"Hadi Muhammad Usman","year":"2023","unstructured":"Muhammad Usman Hadi, R Qureshi, A Shah, M Irfan, A Zafar, MB Shaikh, N Akhtar, J Wu, and S Mirjalili. 2023. A survey on large language models: Applications, challenges, limitations, and practical usage. TechRxiv (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_14_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_15_1","volume-title":"Tianyu Pang, Chao Du, and Min Lin.","author":"Huang Chengsong","year":"2023","unstructured":"Chengsong Huang, Qian Liu, Bill Yuchen Lin, Tianyu Pang, Chao Du, and Min Lin. 2023. LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition. arXiv preprint arXiv:2307.13269 (2023)."},{"key":"e_1_3_2_1_16_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Ilharco Gabriel","year":"2022","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2022. Editing models with task arithmetic. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of NAACL-HLT. 4171--4186","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171--4186."},{"key":"e_1_3_2_1_18_1","volume-title":"E4SRec: An elegant effective efficient extensible solution of large language models for sequential recommendation. arXiv preprint arXiv:2312.02443","author":"Li Xinhang","year":"2023","unstructured":"Xinhang Li, Chong Chen, Xiangyu Zhao, Yong Zhang, and Chunxiao Xing. 2023. E4SRec: An elegant effective efficient extensible solution of large language models for sequential recommendation. arXiv preprint arXiv:2312.02443 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM. arXiv preprint arXiv:2312.15450","author":"Li Xiaopeng","year":"2023","unstructured":"Xiaopeng Li, Lixin Su, Pengyue Jia, Xiangyu Zhao, Suqi Cheng, Junfeng Wang, and Dawei Yin. 2023. Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM. arXiv preprint arXiv:2312.15450 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"e_1_3_2_1_23_1","volume-title":"Large Language Model Distilling Medication Recommendation Model. arXiv preprint arXiv:2402.02803","author":"Liu Qidong","year":"2024","unstructured":"Qidong Liu, Xian Wu, Xiangyu Zhao, Yuanshao Zhu, Zijian Zhang, Feng Tian, and Yefeng Zheng. 2024. Large Language Model Distilling Medication Recommendation Model. arXiv preprint arXiv:2402.02803 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"e_1_3_2_1_25_1","volume-title":"GPT understands, too. AI Open","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023. GPT understands, too. AI Open (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583467"},{"key":"e_1_3_2_1_27_1","volume-title":"RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation. arXiv preprint arXiv:2312.16018","author":"Luo Sichun","year":"2023","unstructured":"Sichun Luo, Bowei He, Haohan Zhao, Yinya Huang, Aojun Zhou, Zongpeng Li, Yuanzhang Xiao, Mingjie Zhan, and Linqi Song. 2023. RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendation. arXiv preprint arXiv:2312.16018 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation. arXiv preprint arXiv:2401.13870","author":"Luo Sichun","year":"2024","unstructured":"Sichun Luo, Yuxuan Yao, Bowei He, Yinya Huang, Aojun Zhou, Xinyi Zhang, Yuanzhang Xiao, Mingjie Zhan, and Linqi Song. 2024. Integrating Large Language Models into Recommendation via Mutual Augmentation and Adaptive Aggregation. arXiv preprint arXiv:2401.13870 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Curtis P Langlotz, and Dan Jurafsky.","author":"Miura Yasuhide","year":"2020","unstructured":"Yasuhide Miura, Yuhao Zhang, Emily Bao Tsai, Curtis P Langlotz, and Dan Jurafsky. 2020. Improving factual completeness and consistency of image-totext radiology report generation. arXiv preprint arXiv:2010.10042 (2020)."},{"key":"e_1_3_2_1_30_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Macro f1 and macro f1. arXiv preprint arXiv:1911.03347","author":"Opitz Juri","year":"2019","unstructured":"Juri Opitz and Sebastian Burst. 2019. Macro f1 and macro f1. arXiv preprint arXiv:1911.03347 (2019)."},{"key":"e_1_3_2_1_32_1","volume-title":"MNN: Multimodal Attentional Neural Networks for Diagnosis Prediction. In International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:199466261","author":"Qiao Zhi","year":"2019","unstructured":"Zhi Qiao, X. Wu, Shen Ge, and Wei Fan. 2019. MNN: Multimodal Attentional Neural Networks for Diagnosis Prediction. In International Joint Conference on Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:199466261"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-21014-3_28"},{"key":"e_1_3_2_1_34_1","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume":"34","author":"Riquelme Carlos","year":"2021","unstructured":"Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, Andr\u00e9 Susano Pinto, Daniel Keysers, and Neil Houlsby. 2021. Scaling vision with sparse mixture of experts. Advances in Neural Information Processing Systems 34 (2021), 8583--8595.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_35_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3481941"},{"key":"e_1_3_2_1_37_1","volume-title":"Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al.","author":"Singhal Karan","year":"2023","unstructured":"Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. 2023. Large language models encode clinical knowledge. Nature 620, 7972 (2023), 172--180."},{"key":"e_1_3_2_1_38_1","unstructured":"Karan Singhal Tao Tu Juraj Gottweis Rory Sayres Ellery Wulczyn Le Hou Kevin Clark Stephen Pfohl Heather Cole-Lewis Darlene Neal et al. 2023. Towards expert-level medical question answering with large language models. arXiv preprint arXiv:2305.09617 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.625"},{"key":"e_1_3_2_1_40_1","volume-title":"LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Hyper-X: A unified hypernetwork for multi-task multilingual transfer. arXiv preprint arXiv:2205.12148","author":"\u00dcst\u00fcn Ahmet","year":"2022","unstructured":"Ahmet \u00dcst\u00fcn, Arianna Bisazza, Gosse Bouma, Gertjan van Noord, and Sebastian Ruder. 2022. Hyper-X: A unified hypernetwork for multi-task multilingual transfer. arXiv preprint arXiv:2205.12148 (2022)."},{"key":"e_1_3_2_1_42_1","unstructured":"Haochun Wang Chi Liu Nuwa Xi Zewen Qiang Sendong Zhao Bing Qin and Ting Liu. 2023. HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledge. arXiv:2304.06975 [cs.CL]"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Lei Wang Chen Ma Xueyang Feng Zeyu Zhang Hao Yang Jingsen Zhang Zhiyuan Chen Jiakai Tang Xu Chen Yankai Lin et al. 2023. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432 (2023).","DOI":"10.1007\/s11704-024-40231-1"},{"key":"e_1_3_2_1_44_1","volume-title":"Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup. arXiv preprint arXiv:2312.05795","author":"Wang Maolin","year":"2023","unstructured":"Maolin Wang, Yao Zhao, Jiajia Liu, Jingdong Chen, Chenyi Zhuang, Jinjie Gu, Ruocheng Guo, and Xiangyu Zhao. 2023. Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup. arXiv preprint arXiv:2312.05795 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang.","author":"Wang Yuhao","year":"2023","unstructured":"Yuhao Wang, Ha Tsz Lam, Yi Wong, Ziru Liu, Xiangyu Zhao, Yichao Wang, Bo Chen, Huifeng Guo, and Ruiming Tang. 2023. Multi-task deep recommender systems: A survey. arXiv preprint arXiv:2302.03525 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Nested named entity recognition: a survey. ACM Transactions on Knowledge Discovery from Data (TKDD) 16, 6","author":"Wang Yu","year":"2022","unstructured":"Yu Wang, Hanghang Tong, Ziye Zhu, and Yun Li. 2022. Nested named entity recognition: a survey. ACM Transactions on Knowledge Discovery from Data (TKDD) 16, 6 (2022), 1--29."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591750"},{"key":"e_1_3_2_1_49_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824--24837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_50_1","volume-title":"Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models. arXiv preprint arXiv:2403.01972","author":"Xu Derong","year":"2024","unstructured":"Derong Xu, Ziheng Zhang, Zhenxi Lin, Xian Wu, Zhihong Zhu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, and Enhong Chen. 2024. Multi-perspective Improvement of Knowledge Graph Completion with Large Language Models. arXiv preprint arXiv:2403.01972 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models. arXiv preprint arXiv:2402.18099","author":"Xu Derong","year":"2024","unstructured":"Derong Xu, Ziheng Zhang, Zhihong Zhu, Zhenxi Lin, Qidong Liu, Xian Wu, Tong Xu, Xiangyu Zhao, Yefeng Zheng, and Enhong Chen. 2024. Editing Factual Knowledge and Explanatory Ability of Medical Large Language Models. arXiv preprint arXiv:2402.18099 (2024)."},{"key":"e_1_3_2_1_52_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Chao Yin Chenxu Lv Da Pan Dian Wang Dong Yan Fan Yang et al. 2023. Baichuan 2: Open Largescale Language Models. arXiv preprint arXiv:2309.10305 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Chatdoctor: A medical chat model fine-tuned on llama model using medical domain knowledge. arXiv preprint arXiv:2303.14070","author":"Yunxiang Li","year":"2023","unstructured":"Li Yunxiang, Li Zihan, Zhang Kai, Dan Ruilong, and Zhang You. 2023. Chatdoctor: A medical chat model fine-tuned on llama model using medical domain knowledge. arXiv preprint arXiv:2303.14070 (2023)."},{"key":"e_1_3_2_1_54_1","volume-title":"Pushing mixture of experts to the limit: Extremely parameter efficient moe for instruction tuning. arXiv preprint arXiv:2309.05444","author":"Zadouri Ted","year":"2023","unstructured":"Ted Zadouri, Ahmet \u00dcst\u00fcn, Arash Ahmadian, Beyza Ermi?, Acyr Locatelli, and Sara Hooker. 2023. Pushing mixture of experts to the limit: Extremely parameter efficient moe for instruction tuning. arXiv preprint arXiv:2309.05444 (2023)."},{"key":"e_1_3_2_1_55_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Zeng Aohan","year":"2022","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, et al. 2022. GLM-130B: An Open Bilingual Pre-trained Model. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_56_1","unstructured":"Shengyu Zhang Linfeng Dong Xiaoya Li Sen Zhang Xiaofei Sun Shuhe Wang Jiwei Li Runyi Hu Tianwei Zhang Fei Wu et al. 2023. Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Article 17 (jan","author":"Zhang Yingying","year":"2023","unstructured":"Yingying Zhang, Xian Wu, Quan Fang, Shengsheng Qian, and Changsheng Xu. 2023. Knowledge-Enhanced Attributed Multi-Task Learning for Medicine Recommendation. ACM Trans. Inf. Syst., Article 17 (jan 2023), 24 pages."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301817"},{"key":"e_1_3_2_1_60_1","volume-title":"Harnessing Large Language Models for Text-Rich Sequential Recommendation. arXiv preprint arXiv:2403.13325","author":"Zheng Zhi","year":"2024","unstructured":"Zhi Zheng, Wenshuo Chao, Zhaopeng Qiu, Hengshu Zhu, and Hui Xiong. 2024. Harnessing Large Language Models for Text-Rich Sequential Recommendation. arXiv preprint arXiv:2403.13325 (2024)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539201"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511020"},{"key":"e_1_3_2_1_63_1","volume-title":"PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain. arXiv preprint arXiv:2310.14151","author":"Zhu Wei","year":"2023","unstructured":"Wei Zhu, Xiaoling Wang, Huanran Zheng, Mosha Chen, and Buzhou Tang. 2023. PromptCBLUE: A Chinese Prompt Tuning Benchmark for the Medical Domain. arXiv preprint arXiv:2310.14151 (2023)."}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657722","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3657722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:43:27Z","timestamp":1755841407000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3657722"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":63,"alternative-id":["10.1145\/3626772.3657722","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3657722","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}