{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:10:05Z","timestamp":1755889805802,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3729938","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:18:36Z","timestamp":1752455916000},"page":"1402-1412","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CSE-SFP: Enabling Unsupervised Sentence Representation Learning via a Single Forward Pass"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2550-6468","authenticated-orcid":false,"given":"Bowen","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9111-3866","authenticated-orcid":false,"given":"Zixin","family":"Song","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4521-0875","authenticated-orcid":false,"given":"Chunping","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961","author":"BehnamGhader Parishad","year":"2024","unstructured":"Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach, Dzmitry Bahdanau, Nicolas Chapados, and Siva Reddy. 2024. Llm2vec: Large language models are secretly powerful text encoders. arXiv preprint arXiv:2404.05961 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3495883"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.197"},{"key":"e_1_3_2_1_4_1","first-page":"240","article-title":"2023. Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research, Vol. 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.311"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Conneau Alexis","year":"2018","unstructured":"Alexis Conneau and Douwe Kiela. 2018. SentEval: An Evaluation Toolkit for Universal Sentence Representations. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). European Language Resources Association (ELRA), Miyazaki, Japan. https:\/\/aclanthology.org\/L18--1269\/"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Dettmers Tim","year":"2024","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2024. QLORA: efficient finetuning of quantized LLMs. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '23). Curran Associates Inc., Red Hook, NY, USA, Article 441, 28 pages."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19--1423"},{"key":"e_1_3_2_1_9_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19--1006"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","volume-title":"Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al.","author":"Hoffmann Jordan","year":"2022","unstructured":"Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. 2022. Training compute-optimal large language models. arXiv preprint arXiv:2203.15556 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al.","author":"Jiang Albert Q","year":"2023","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, et al. 2023. Mistral 7B. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.181"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.603"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"e_1_3_2_1_18_1","volume-title":"DeeLM: Dependency-enhanced Large Language Model for Sentence Embeddings. arXiv preprint arXiv:2311.05296","author":"Li Xianming","year":"2023","unstructured":"Xianming Li and Jing Li. 2023. DeeLM: Dependency-enhanced Large Language Model for Sentence Embeddings. arXiv preprint arXiv:2311.05296 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.771"},{"key":"e_1_3_2_1_20_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, Vol. 364 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"Generative representational instruction tuning. arXiv preprint arXiv:2402.09906","author":"Muennighoff Niklas","year":"2024","unstructured":"Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, and Douwe Kiela. 2024. Generative representational instruction tuning. arXiv preprint arXiv:2402.09906 (2024)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"e_1_3_2_1_23_1","volume-title":"Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748","author":"van den Oord Aaron","year":"2018","unstructured":"Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 18th Conference of the European","author":"Kashyap Abhinav Ramesh","year":"2024","unstructured":"Abhinav Ramesh Kashyap, Thanh-Tung Nguyen, Viktor Schlegel, Stefan Winkler, See-Kiong Ng, and Soujanya Poria. 2024. A Comprehensive Survey of Sentence Representations: From the BERT Epoch to the CHATGPT Era and Beyond. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, St. Julian's, Malta, 1738--1751. https:\/\/aclanthology.org\/2024.eacl-long.104"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19--1410"},{"key":"e_1_3_2_1_26_1","volume-title":"Revisiting over-smoothing in bert from the perspective of graph. arXiv preprint arXiv:2202.08625","author":"Shi Han","year":"2022","unstructured":"Han Shi, Jiahui Gao, Hang Xu, Xiaodan Liang, Zhenguo Li, Lingpeng Kong, Stephen Lee, and James T Kwok. 2022. Revisiting over-smoothing in bert from the perspective of graph. arXiv preprint arXiv:2202.08625 (2022)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.448"},{"key":"e_1_3_2_1_28_1","unstructured":"Shaden Smith Mostofa Patwary Brandon Norick Patrick LeGresley Samyam Rajbhandari Jared Casper Zhun Liu Shrimai Prabhumoye George Zerveas Vijay Korthikanti et al. 2022. Using deepspeed and megatron to train megatron-turing nlg 530b a large-scale generative language model. arXiv preprint arXiv:2201.11990 (2022)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357895"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.22"},{"key":"e_1_3_2_1_31_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--981--99--4752--2_35"},{"key":"e_1_3_2_1_34_1","volume-title":"Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368","author":"Wang Liang","year":"2023","unstructured":"Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2023a. Improving text embeddings with large language models. arXiv preprint arXiv:2401.00368 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110381"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research","author":"Wang Tongzhou","year":"2020","unstructured":"Tongzhou Wang and Phillip Isola. 2020. Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere. In Proceedings of the 37th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 119), Hal Daum\u00e9 III and Aarti Singh (Eds.). PMLR, 9929--9939. https:\/\/proceedings.mlr.press\/v119\/wang20k.html"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.520"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531823"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 3898--3907","author":"Wu Xing","year":"2022","unstructured":"Xing Wu, Chaochen Gao, Liangjun Zang, Jizhong Han, Zhongyuan Wang, and Songlin Hu. 2022. ESimCSE: Enhanced Sample Building Method for Contrastive Learning of Unsupervised Sentence Embedding. In Proceedings of the 29th International Conference on Computational Linguistics. International Committee on Computational Linguistics, Gyeongju, Republic of Korea, 3898--3907."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.393"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-031--72350--6_10"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--981--97--5669--8_5"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.663"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.791"},{"key":"e_1_3_2_1_45_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_46_1","volume-title":"Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473","author":"Zhao Penghao","year":"2024","unstructured":"Penghao Zhao, Hailin Zhang, Qinhan Yu, Zhengren Wang, Yunteng Geng, Fangcheng Fu, Ling Yang, Wentao Zhang, and Bin Cui. 2024. Retrieval-augmented generation for ai-generated content: A survey. arXiv preprint arXiv:2402.19473 (2024)."}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"],"location":"Padua Italy","acronym":"SIGIR '25"},"container-title":["Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3726302.3729938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T18:33:16Z","timestamp":1755887596000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3729938"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":46,"alternative-id":["10.1145\/3726302.3729938","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3729938","relation":{},"subject":[],"published":{"date-parts":[[2025,7,13]]},"assertion":[{"value":"2025-07-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}