{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:42:23Z","timestamp":1778812943690,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":81,"publisher":"ACM","funder":[{"name":"Chinese NSF Major Research Plan","award":["No.92270121"],"award-info":[{"award-number":["No.92270121"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736985","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T20:52:41Z","timestamp":1754254361000},"page":"2126-2137","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["GORACS: Group-level Optimal Transport-guided Coreset Selection for LLM-based Recommender Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-9677-4653","authenticated-orcid":false,"given":"Tiehua","family":"Mei","sequence":"first","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3310-9224","authenticated-orcid":false,"given":"Hengrui","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0335-9152","authenticated-orcid":false,"given":"Peng","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0670-5602","authenticated-orcid":false,"given":"Jiaqing","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1390-3861","authenticated-orcid":false,"given":"Deqing","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Data Science, Fudan University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Abhinab Acharya Dayou Yu Qi Yu and Xumin Liu. 2024. Balancing Feature Similarity and Label Variability for Optimal Size-Aware One-shot Subset Selection. In ICML."},{"key":"e_1_3_2_2_2_1","unstructured":"Keqin Bao Jizhi Zhang Wenjie Wang Yang Zhang Zhengyi Yang Yancheng Luo Fuli Feng Xiangnan He and Qi Tian. 2023a. A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems. arxiv:2308.08434"},{"key":"e_1_3_2_2_3_1","volume-title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation. In RecSys.","author":"Bao Keqin","year":"2023","unstructured":"Keqin Bao, Jizhi Zhang, Yang Zhang, Wenjie Wang, Fuli Feng, and Xiangnan He. 2023b. Tallrec: An effective and efficient tuning framework to align large language model with recommendation. In RecSys."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2600425"},{"key":"e_1_3_2_2_5_1","unstructured":"Zal\u00e1n Borsos Mojmir Mutny and Andreas Krause. 2020. Coresets via Bilevel Optimization for Continual Learning and Streaming. In NeurIPS."},{"key":"e_1_3_2_2_6_1","volume-title":"Lukasz Heldt, Lichan Hong, Ed Chi, and Maheswaran Sathiamoorthy.","author":"Cao Yuwei","year":"2024","unstructured":"Yuwei Cao, Nikhil Mehta, Xinyang Yi, Raghunandan Hulikal Keshavan, Lukasz Heldt, Lichan Hong, Ed Chi, and Maheswaran Sathiamoorthy. 2024. Aligning Large Language Models with Recommendation Knowledge. In Findings of NAACL."},{"key":"e_1_3_2_2_7_1","volume-title":"HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling. arxiv:2409.12740","author":"Chen Junyi","year":"2024","unstructured":"Junyi Chen, Lu Chi, Bingyue Peng, and Zehuan Yuan. 2024. HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling. arxiv:2409.12740"},{"key":"e_1_3_2_2_8_1","volume-title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transport. In NeurIPS.","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn Distances: Lightspeed Computation of Optimal Transport. In NeurIPS."},{"key":"e_1_3_2_2_9_1","first-page":"63","volume-title":"Structural Optimization","volume":"14","author":"Das Indraneel","year":"1997","unstructured":"Indraneel Das and J. Dennis. 1997. A Closer Look at Drawbacks of Minimizing Weighted Sums of Objectives for Pareto Set Generation in Multicriteria Optimization Problems. Structural Optimization, Vol. 14 (01 1997), 63-69."},{"key":"e_1_3_2_2_10_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and other. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL."},{"key":"e_1_3_2_2_11_1","volume-title":"TAROT: Targeted Data Selection via Optimal Transport. arxiv:2412.00420","author":"Feng Lan","year":"2024","unstructured":"Lan Feng, Fan Nie, Yuejiang Liu, and Alexandre Alahi. 2024. TAROT: Targeted Data Selection via Optimal Transport. arxiv:2412.00420"},{"key":"e_1_3_2_2_12_1","article-title":"POT: Python optimal transport","volume":"22","author":"Flamary R\u00e9mi","year":"2021","unstructured":"R\u00e9mi Flamary, Nicolas Courty, Alexandre Gramfort, et al., 2021. POT: Python optimal transport. J. Mach. Learn. Res., Vol. 22, 1, Article 78 (Jan. 2021), 8 pages.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_13_1","unstructured":"Yunfan Gao Tao Sheng Youlin Xiang Yun Xiong Haofen Wang and Jiawei Zhang. 2023. Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System. arxiv:2303.14524"},{"key":"e_1_3_2_2_14_1","volume-title":"Gower","author":"Garrigos Guillaume","year":"2024","unstructured":"Guillaume Garrigos and Robert M. Gower. 2024. Handbook of Convergence Theorems for (Stochastic) Gradient Methods. arxiv:2301.11235"},{"key":"e_1_3_2_2_15_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The Llama 3 Herd of Models. arxiv:2407.21783"},{"key":"e_1_3_2_2_16_1","unstructured":"Chengcheng Guo Bo Zhao and Yanbing Bai. 2022. DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning. In DEXA."},{"key":"e_1_3_2_2_17_1","volume-title":"Jordan","author":"Guo Wenshuo","year":"2020","unstructured":"Wenshuo Guo, Nhat Ho, and Michael I. Jordan. 2020. Fast Algorithms for Computational Optimal Transport and Wasserstein Barycenter. In AISTATS."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2021.101656"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0966-8349(98)00030-8"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"Yupeng Hou Junjie Zhang Zihan Lin Hongyu Lu Ruobing Xie Julian J. McAuley and Wayne Xin Zhao. 2024. Large Language Models are Zero-Shot Rankers for Recommender Systems. In ECIR.","DOI":"10.1007\/978-3-031-56060-6_24"},{"key":"e_1_3_2_2_21_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR."},{"key":"e_1_3_2_2_22_1","volume-title":"Ma","author":"Hu Yuzheng","year":"2024","unstructured":"Yuzheng Hu, Pingbang Hu, Han Zhao, and Jiaqi W. Ma. 2024. Most Influential Subset Selection: Challenges, Promises, and Beyond. arxiv:2409.18153"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3569930"},{"key":"e_1_3_2_2_24_1","volume-title":"Devendra Singh Chaplot, et al","author":"Jiang Albert Q.","year":"2023","unstructured":"Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, et al., 2023. Mistral 7B. arxiv:2310.06825"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Meng Jiang Keqin Bao Jizhi Zhang Wenjie Wang Zhengyi Yang Fuli Feng and Xiangnan He. 2024. Item-side Fairness of Large Language Model-based Recommendation System. In WWW.","DOI":"10.1145\/3589334.3648158"},{"key":"e_1_3_2_2_26_1","volume-title":"Chen","author":"Joaquin Ayrton San","year":"2024","unstructured":"Ayrton San Joaquin, Bin Wang, Zhengyuan Liu, Nicholas Asher, Brian Lim, Philippe Muller, and Nancy F. Chen. 2024. In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models. In Findings of EMNLP."},{"key":"e_1_3_2_2_27_1","volume-title":"LAVA: Data Valuation without Pre-Specified Learning Algorithms. In ICLR.","author":"Just Hoang Anh","year":"2023","unstructured":"Hoang Anh Just, Feiyang Kang, Tianhao Wang, Yi Zeng, Myeongseob Ko, Ming Jin, and Ruoxi Jia. 2023. LAVA: Data Valuation without Pre-Specified Learning Algorithms. In ICLR."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.envsoft.2018.03.031"},{"key":"e_1_3_2_2_29_1","volume-title":"Yifan Sun, Himanshu Jahagirdar, Yuanzhi Zhang, Rongxing Du, Anit Kumar Sahu, and Ruoxi Jia.","author":"Kang Feiyang","year":"2024","unstructured":"Feiyang Kang, Hoang Anh Just, Yifan Sun, Himanshu Jahagirdar, Yuanzhi Zhang, Rongxing Du, Anit Kumar Sahu, and Ruoxi Jia. 2024. Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs. In ICLR."},{"key":"e_1_3_2_2_30_1","volume-title":"McAuley","author":"Kang Wang-Cheng","year":"2018","unstructured":"Wang-Cheng Kang and Julian J. McAuley. 2018. Self-Attentive Sequential Recommendation. In ICDM."},{"key":"e_1_3_2_2_31_1","volume-title":"Chi, and Derek Zhiyuan Cheng","author":"Kang Wang-Cheng","year":"2023","unstructured":"Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed H. Chi, and Derek Zhiyuan Cheng. 2023. Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction. arxiv:2305.06474"},{"key":"e_1_3_2_2_32_1","first-page":"52","article-title":"On a space of totally additive functions","volume":"13","author":"Kantorovich Leonid","year":"1958","unstructured":"Leonid Kantorovich and Gennady S. Rubinstein. 1958. On a space of totally additive functions. Vestnik Leningrad. Univ, Vol. 13 (1958), 52-59.","journal-title":"Vestnik Leningrad. Univ"},{"key":"e_1_3_2_2_33_1","volume-title":"Iyer","author":"Killamsetty KrishnaTeja","year":"2021","unstructured":"KrishnaTeja Killamsetty, Durga Sivasubramanian, Ganesh Ramakrishnan, and Rishabh K. Iyer. 2021a. GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning. In AAAI."},{"key":"e_1_3_2_2_34_1","volume-title":"Iyer","author":"Killamsetty KrishnaTeja","year":"2021","unstructured":"KrishnaTeja Killamsetty, Xujiang Zhao, Feng Chen, and Rishabh K. Iyer. 2021b. RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning. In NeurIPS."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.9.4.643"},{"key":"e_1_3_2_2_36_1","unstructured":"Riwei Lai Li Chen Rui Chen and Chi Zhang. 2024. A Survey on Data-Centric Recommender Systems. arxiv:2401.17878"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"crossref","unstructured":"Lei Li Yongfeng Zhang and Li Chen. 2023. Prompt Distillation for Efficient LLM-based Recommendation. In CIKM.","DOI":"10.1145\/3583780.3615017"},{"key":"e_1_3_2_2_38_1","unstructured":"Ming Li Yong Zhang Zhitao Li Jiuhai Chen Lichang Chen Ning Cheng Jianzong Wang Tianyi Zhou and Jing Xiao. 2024. From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning. In NAACL."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"Xinyu Lin Wenjie Wang Yongqi Li Shuo Yang Fuli Feng Yinwei Wei and Tat-Seng Chua. 2024. Data-efficient Fine-tuning for LLM-based Recommendation. In SIGIR.","DOI":"10.1145\/3626772.3657807"},{"key":"e_1_3_2_2_40_1","unstructured":"Junling Liu Chao Liu Renjie Lv Kang Zhou and Yan Zhang. 2023. Is ChatGPT a Good Recommender? A Preliminary Study. arxiv:2304.10149"},{"key":"e_1_3_2_2_41_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv:1907.11692"},{"key":"e_1_3_2_2_42_1","volume-title":"Alexander Felfernig, Seda Polat Erdeniz, and Viet-Man Le.","author":"Lubos Sebastian","year":"2024","unstructured":"Sebastian Lubos, Thi Ngoc Trang Tran, Alexander Felfernig, Seda Polat Erdeniz, and Viet-Man Le. 2024. LLM-generated Explanations for Recommender Systems. In UMAP."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"crossref","unstructured":"Hanjia Lyu Song Jiang Hanqing Zeng Yinglong Xia Qifan Wang Si Zhang Ren Chen Christopher Leung Jiajie Tang and Jiebo Luo. 2024. LLM-Rec: Personalized Recommendation via Prompting Large Language Models. In Findings of NAACL.","DOI":"10.18653\/v1\/2024.findings-naacl.39"},{"key":"e_1_3_2_2_44_1","unstructured":"Adyasha Maharana Prateek Yadav and Mohit Bansal. 2024. D2 Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning. In ICLR."},{"key":"e_1_3_2_2_45_1","unstructured":"Max Marion Ahmet \u00dcst\u00fcn Luiza Pozzobon Alex Wang Marzieh Fadaee and Sara Hooker. 2023. When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale. arxiv:2309.04564"},{"key":"e_1_3_2_2_46_1","unstructured":"Baharan Mirzasoleiman Jeff A. Bilmes and Jure Leskovec. 2020. Coresets for Data-efficient Training of Machine Learning Models. In ICML."},{"key":"e_1_3_2_2_47_1","volume-title":"TRAK: Attributing Model Behavior at Scale. In ICML.","author":"Park Sung Min","year":"2023","unstructured":"Sung Min Park, Kristian Georgiev, Andrew Ilyas, Guillaume Leclerc, and Aleksander Madry. 2023. TRAK: Attributing Model Behavior at Scale. In ICML."},{"key":"e_1_3_2_2_48_1","unstructured":"Mansheej Paul Surya Ganguli and Gintare Karolina Dziugaite. 2021. Deep Learning on a Data Diet: Finding Important Examples Early in Training. In NeurIPS."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"e_1_3_2_2_50_1","unstructured":"Omead Pooladzandi David Davini and Baharan Mirzasoleiman. 2022. Adaptive Second Order Coresets for Data-efficient Machine Learning. In ICML."},{"key":"e_1_3_2_2_51_1","volume-title":"INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models. In Findings of EMNLP.","author":"Kowndinya Renduchintala H. S. V. N. S.","year":"2023","unstructured":"H. S. V. N. S. Kowndinya Renduchintala, Krishnateja Killamsetty, Sumit Bhatia, Milan Aggarwal, Ganesh Ramakrishnan, Rishabh K. Iyer, and Balaji Krishnamurthy. 2023. INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models. In Findings of EMNLP."},{"key":"e_1_3_2_2_52_1","volume-title":"Jason Ingyu Choi, and Shervin Malmasi","author":"Senel L\u00fctfi Kerem","year":"2024","unstructured":"L\u00fctfi Kerem Senel, Besnik Fetahu, Davis Yoshida, Zhiyu Chen, Giuseppe Castellucci, Nikhita Vedula, Jason Ingyu Choi, and Shervin Malmasi. 2024. Generative Explore-Exploit: Training-free Optimization of Generative Recommender Systems using LLM Optimizers. In ACL."},{"key":"e_1_3_2_2_53_1","unstructured":"Ben Sorscher Robert Geirhos Shashank Shekhar Surya Ganguli and Ari Morcos. 2022. Beyond neural scaling laws: beating power law scaling via data pruning. In NeurIPS."},{"key":"e_1_3_2_2_54_1","unstructured":"Zhongxiang Sun Zihua Si Xiaoxue Zang Kai Zheng Yang Song Xiao Zhang and Jun Xu. 2024. Large Language Models Enhanced Collaborative Filtering. In CIKM."},{"key":"e_1_3_2_2_55_1","volume-title":"Heuristic methods for estimating the generalized vertex median of a weighted graph. Operations research","author":"Teitz Michael B","year":"1968","unstructured":"Michael B Teitz and Polly Bart. 1968. Heuristic methods for estimating the generalized vertex median of a weighted graph. Operations research, Vol. 16, 5 (1968), 955-961."},{"key":"e_1_3_2_2_56_1","volume-title":"Adam Trischler, Yoshua Bengio, and Geoffrey J. Gordon.","author":"Toneva Mariya","year":"2019","unstructured":"Mariya Toneva, Alessandro Sordoni, Remi Tachet des Combes, Adam Trischler, Yoshua Bengio, and Geoffrey J. Gordon. 2019. An Empirical Study of Example Forgetting during Deep Neural Network Learning. In ICLR."},{"key":"e_1_3_2_2_57_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet et al. 2023. LLaMA: Open and Efficient Foundation Language Models. arxiv:2302.13971"},{"key":"e_1_3_2_2_58_1","volume-title":"Topics in Optimal Transportation","author":"C. Villani and American Mathematical Society","year":"2003","unstructured":"C. Villani and American Mathematical Society. 2003. Topics in Optimal Transportation. American Mathematical Society. 2003040350"},{"key":"e_1_3_2_2_59_1","unstructured":"Jiahao Wang Bolin Zhang Qianlong Du Jiajun Zhang and Dianhui Chu. 2024. A Survey on Data Selection for LLM Instruction Tuning. arxiv:2402.05123"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"crossref","unstructured":"Xiao Wang Weikang Zhou Qi Zhang Jie Zhou Songyang Gao Junzhe Wang Menghan Zhang Xiang Gao Yunwen Chen and Tao Gui. 2023. Farewell to Aimless Large-scale Pretraining: Influential Subset Selection for Language Model. In Findings of ACL.","DOI":"10.18653\/v1\/2023.findings-acl.35"},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"crossref","unstructured":"Wei Wei Xubin Ren Jiabin Tang Qinyong Wang Lixin Su Suqi Cheng Junfeng Wang Dawei Yin and Chao Huang. 2024. LLMRec: Large Language Models with Graph Augmentation for Recommendation. In WSDM.","DOI":"10.1145\/3616855.3635853"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1080\/03155986.1983.11731889"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3484249"},{"key":"e_1_3_2_2_64_1","unstructured":"Jiahao Wu Wenqi Fan Shengcai Liu Qijiong Liu Rui He Qing Li and Ke Tang. 2023. Dataset Condensation for Recommendation. arxiv:2310.01038"},{"key":"e_1_3_2_2_65_1","unstructured":"Likang Wu Zhi Zheng Zhaopeng Qiu Hao Wang Hongchao Gu Tingjia Shen Chuan Qin Chen Zhu Hengshu Zhu Qi Liu Hui Xiong and Enhong Chen. 2024. A survey on large language models for recommendation. WWW(2024)."},{"key":"e_1_3_2_2_66_1","volume-title":"LESS: Selecting Influential Data for Targeted Instruction Tuning. In ICML.","author":"Xia Mengzhou","year":"2024","unstructured":"Mengzhou Xia, Sadhika Malladi, Suchin Gururangan, et al., 2024. LESS: Selecting Influential Data for Targeted Instruction Tuning. In ICML."},{"key":"e_1_3_2_2_67_1","volume-title":"Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep Learning. In ICLR.","author":"Xia Xiaobo","year":"2023","unstructured":"Xiaobo Xia, Jiale Liu, Jun Yu, Xu Shen, Bo Han, and Tongliang Liu. 2023. Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep Learning. In ICLR."},{"key":"e_1_3_2_2_68_1","unstructured":"Shitao Xiao Zheng Liu Peitian Zhang and Niklas Muennighoff. 2023. C-Pack: Packaged Resources To Advance General Chinese Embedding. arxiv:2309.07597"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"crossref","unstructured":"Weiwei Xiao Yongyong Chen Qiben Shan Yaowei Wang and Jingyong Su. 2024. Feature Distribution Matching by Optimal Transport for Effective and Robust Coreset Selection. In AAAI.","DOI":"10.1609\/aaai.v38i8.28771"},{"key":"e_1_3_2_2_70_1","unstructured":"Sang Michael Xie Shibani Santurkar Tengyu Ma and Percy Liang. 2023. Data Selection for Language Models via Importance Resampling. In NeurIPS."},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"crossref","unstructured":"Zhengyi Yang Xiangnan He Jizhi Zhang Jiancan Wu Xin Xin Jiawei Chen and Xiang Wang. 2023. A Generic Learning Framework for Sequential Recommendation with Distribution Shifts. In SIGIR.","DOI":"10.1145\/3539618.3591624"},{"key":"e_1_3_2_2_72_1","volume-title":"Dong Wang, and Even Oldridge.","author":"Yue Zhenrui","year":"2023","unstructured":"Zhenrui Yue, Sara Rabhi, Gabriel de Souza Pereira Moreira, Dong Wang, and Even Oldridge. 2023. LlamaRec: Two-Stage Recommendation using Large Language Models for Ranking. arxiv:2311.02089"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"crossref","unstructured":"Chuanyan Zhang and Xiaoguang Hong. 2021. Challenging the Long Tail Recommendation on Heterogeneous Information Network. In ICDM.","DOI":"10.1109\/ICDMW53433.2021.00018"},{"key":"e_1_3_2_2_74_1","unstructured":"Guoxiao Zhang Yi Wei Yadong Zhang Huajian Feng and Qiang Liu. 2024b. Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction. arxiv:2412.06860"},{"key":"e_1_3_2_2_75_1","unstructured":"Xiaoyu Zhang Juan Zhai Shiqing Ma Chao Shen Tianlin Li Weipeng Jiang and Yang Liu. 2024c. Speculative Coreset Selection for Task-Specific Fine-tuning. arxiv:2410.01296"},{"key":"e_1_3_2_2_76_1","doi-asserted-by":"crossref","unstructured":"Yang Zhang Keqin Bao Ming Yan Wenjie Wang Fuli Feng and Xiangnan He. 2024a. Text-like Encoding of Collaborative Information in Large Language Models for Recommendation. In ACL.","DOI":"10.18653\/v1\/2024.acl-long.497"},{"key":"e_1_3_2_2_77_1","unstructured":"Yang Zhang Fuli Feng Jizhi Zhang Keqin Bao Qifan Wang and Xiangnan He. 2023. CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation. arxiv:2310.19488"},{"key":"e_1_3_2_2_78_1","unstructured":"Yuying Zhao Yu Wang Yunchao Liu Xueqi Cheng Charu C. Aggarwal and Tyler Derr. 2023. Fairness and Diversity in Recommender Systems: A Survey. arxiv:2307.04644"},{"key":"e_1_3_2_2_79_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3392335"},{"key":"e_1_3_2_2_80_1","unstructured":"Haizhong Zheng Rui Liu Fan Lai and Atul Prakash. 2023. Coverage-centric Coreset Selection for High Pruning Rates. In ICLR."},{"key":"e_1_3_2_2_81_1","volume-title":"LIMA: Less Is More for Alignment. In NeurIPS. gr","author":"Zhou Chunting","year":"2023","unstructured":"Chunting Zhou, Pengfei Liu, Puxin Xu, et al., 2023. LIMA: Less Is More for Alignment. In NeurIPS. gr"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:04:32Z","timestamp":1777572272000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736985"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":81,"alternative-id":["10.1145\/3711896.3736985","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736985","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}