{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T15:26:27Z","timestamp":1778599587675,"version":"3.51.4"},"reference-count":47,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Henan Science and Technology Research Project of China","award":["242102211060"],"award-info":[{"award-number":["242102211060"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Unsupervised sentence embedding, vital for numerous NLP tasks, struggles with the inherent asymmetry of semantic relationships within contrastive learning (CL). This paper proposes Label Smoothing-based Ranking Negative Sampling (LS-RNS), a novel framework that directly tackles the semantic asymmetry between anchor and negative samples in CL. LS-RNS utilizes a Large Language Model (LLM) to assess fine-grained asymmetric similarity scores between sentences, constructing a ranking-aware negative sampling strategy combined with adaptive label smoothing. This design encourages the model to learn more effectively from informative negatives that are semantically closer to the anchor, leading to asymmetry-aware sentence embeddings. Experiments on standard Semantic Textual Similarity (STS) benchmarks (STS12\u2013STS16, STS-B, SICK-R) show that LS-RNS achieves state-of-the-art performance. We adopt Spearman\u2019s rank correlation coefficient as the primary evaluation metric for semantic similarity tasks, and we use classification accuracy for downstream and transfer tasks. LS-RNS achieves 79.87 on STS tasks with BERT-base (vs. 76.25 for SimCSE, +3.62) and 80.41 with RoBERTa-base (vs. 79.18 for DiffCSE). On transfer tasks, it attains 88.82 (BERT) and 87.68 (RoBERTa), consistently outperforming PromptBERT and SNCSE. On STL-10, LS-RNS improves SimCLR top-one accuracy from 79.50% to 80.52% with ResNet-18 and from 68.91% to 72.19% with VGG-16, even enabling a shallow ResNet-18 to surpass a deeper ResNet-34 baseline. These results confirm the modality-agnostic effectiveness of LS-RNS and its potential to redefine contrastive learning objectives by modeling semantic asymmetry, rather than relying solely on encoder depth or pre-training objectives.<\/jats:p>","DOI":"10.3390\/sym17050646","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T08:02:57Z","timestamp":1745568177000},"page":"646","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Addressing Asymmetry in Contrastive Learning: LLM-Driven Sentence Embeddings with Ranking and Label Smoothing"],"prefix":"10.3390","volume":"17","author":[{"given":"Yan","family":"Huang","sequence":"first","affiliation":[{"name":"College of Software, Zhengzhou University of Light Industry, Zhengzhou 450066, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoben","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan 430072, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2649-3464","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Software, Zhengzhou University of Light Industry, Zhengzhou 450066, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Software, Zhengzhou University of Light Industry, Zhengzhou 450066, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinheng","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Software, Zhengzhou University of Light Industry, Zhengzhou 450066, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"ref_1","unstructured":"Le, Q., and Mikolov, T. (2014, January 21\u201326). Distributed Representations of Sentences and Documents. Proceedings of the International Conference on Machine Learning, Beijing, China."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Reimers, N., and Gurevych, I. (2019, January 3\u20137). Sentence-Bert: Sentence Embeddings Using Siamese Bert-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong.","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"84134","DOI":"10.1109\/ACCESS.2023.3302913","article-title":"Self-Supervised and Few-Shot Contrastive Learning Frameworks for Text Clustering","volume":"11","author":"Shi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s10115-023-01925-3","article-title":"Mining parallel sentences from internet with multi-view knowledge distillation for low-resource language pairs","volume":"66","author":"Zhu","year":"2024","journal-title":"Knowl. Inf. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kellert, O., and Mahmud Uz Zaman, M. (2022, January 26\u201327). Using Neural Topic Models to Track Context Shifts of Words: A Case Study of COVID-Related Terms Before and After the Lockdown in April 2020. Proceedings of the 3rd Workshop on Computational Approaches to Historical Language Change, Dublin, Ireland.","DOI":"10.18653\/v1\/2022.lchange-1.14"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhu, R., Zhao, B., Liu, J., Sun, Z., and Chen, C.W. (2021, January 11\u201317). Improving Contrastive Learning by Visualizing Feature Transformation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01014"},{"key":"ref_7","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume":"Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"ref_8","unstructured":"Zhuang, L., Wayne, L., Ya, S., and Jun, Z. (2021, January 13\u201315). A Robustly Optimized BERT Pre-Training Approach with Post-Training. Proceedings of the 20th Chinese National Conference on Computational Linguistics, Hohhot, China."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ethayarajh, K. (2019, January 3\u20137). How Contextual Are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP 2019), Hong Kong.","DOI":"10.18653\/v1\/D19-1006"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhu, S., Mi, C., and Zhang, L. (2021, January 14\u201316). Inducing Bilingual Word Representations for Non-Isomorphic Spaces by an Unsupervised Way. Proceedings of the International Conference on Knowledge Science, Engineering and Management, Tokyo, Japan.","DOI":"10.1007\/978-3-030-82136-4_37"},{"key":"ref_11","unstructured":"Carlsson, F., Gyllensten, A.C., Gogoulou, E., Hellqvist, E.Y., and Sahlgren, M. (2020, January 30). Semantic Re-Tuning with Contrastive Tension. Proceedings of the 9th International Conference on Learning Representations, Addis Ababa, Ethiopia."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, Y., He, R., Liu, Z., Lim, K.H., and Bing, L. (2020, January 16\u201320). An Unsupervised Sentence Embedding Method by Mutual Information Maximization. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), Online Conference.","DOI":"10.18653\/v1\/2020.emnlp-main.124"},{"key":"ref_13","first-page":"879","article-title":"Declutr: Deep Contrastive learning for unsupervised textual representations","volume":"Volume 1: Long Papers","author":"Giorgi","year":"2021","journal-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Gao, T., Yao, X., and Chen, D. (2021, January 7\u201311). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Online Conference.","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref_15","first-page":"1","article-title":"Unsupervised parallel sentences of machine translation for Asian language pairs","volume":"22","author":"Zhu","year":"2023","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Sun, Y., Zhu, S., Yifan, F., and Mi, C. (2021, January 6\u201311). Parallel Sentences Mining with Transfer Learning in an Unsupervised Setting. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, Online Conference.","DOI":"10.18653\/v1\/2021.naacl-srw.17"},{"key":"ref_17","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"Mikolov","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., and Manning, C.D. (2014, January 25\u201329). Glove: Global Vectors for Word Representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar.","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref_19","first-page":"3294","article-title":"Skip-thought vectors","volume":"28","author":"Kiros","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Hill, F., Cho, K., and Korhonen, A. (2016, January 12\u201317). Learning Distributed Representations of Sentences from Unlabelled Data. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA.","DOI":"10.18653\/v1\/N16-1162"},{"key":"ref_21","first-page":"4892","article-title":"A contrastive framework for learning sentence representations from pairwise and triple-wise perspective in angular space","volume":"Volume 1: Long Papers","author":"Zhang","year":"2022","journal-title":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Li, B., Zhou, H., He, J., Wang, M., Yang, Y., and Li, L. (2020, January 16\u201320). On the Sentence Embeddings from Pre-Trained Language Models. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), Online Conference.","DOI":"10.18653\/v1\/2020.emnlp-main.733"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, J., Tang, D., Zhong, W., Lu, S., Shou, L., Gong, M., Jiang, D., and Duan, N. (2021, January 16\u201320). WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach. Proceedings of the Findings of the Association for Computational Linguistics (EMNLP 2021), Punta Cana, Dominican Republic.","DOI":"10.18653\/v1\/2021.findings-emnlp.23"},{"key":"ref_24","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. (2020, January 13\u201318). A simple Framework for Contrastive Learning of Visual Representations. Proceedings of the International Conference on Machine Learning, Online Conference."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., and Girshick, R. (2020, January 13\u201319). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chuang, Y.S., Dangovski, R., Luo, H., Zhang, Y., Chang, S., Solja\u010di\u0107, M., Li, S.W., Yih, W.t., Kim, Y., and Glass, J. (2022, January 10\u201315). DiffCSE: Difference-Based Contrastive Learning for Sentence Embeddings. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Seattle, WA, USA.","DOI":"10.18653\/v1\/2022.naacl-main.311"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Jiang, T., Jiao, J., Huang, S., Zhang, Z., Wang, D., Zhuang, F., Wei, F., Huang, H., Deng, D., and Zhang, Q. (2022, January 7\u201311). Promptbert: Improving Bert Sentence Embeddings with Prompts. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-main.603"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, H., and Dou, Y. (2023, January 10\u201313). SNCSE: Contrastive Learning for Unsupervised Sentence Embedding with Soft Negative Samples. Proceedings of the International Conference on Intelligent Computing, Zhengzhou, China.","DOI":"10.1007\/978-981-99-4752-2_35"},{"key":"ref_29","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhu, S., Mi, C., and Shi, X. (2021). An Explainable Evaluation of Unsupervised Transfer Learning for Parallel Sentences Mining. Web and Big Data, Proceedings of the 5th International Joint Conference (APWeb-WAIM 2021), Guangzhou, China, 23\u201325 August 2021, Springer. Proceedings, Part I 5.","DOI":"10.1007\/978-3-030-85896-4_22"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Suresh, V., and Ong, D.C. (2021, January 7\u201311). Not All Negatives Are Equal: Label-Aware Contrastive Loss for Fine-Grained Text Classification. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Punta Cana, Dominican Republic.","DOI":"10.18653\/v1\/2021.emnlp-main.359"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Huynh, T., Kornblith, S., Walter, M.R., Maire, M., and Khademi, M. (2022, January 3\u20138). Boosting Contrastive Self-Supervised Learning with False Negative Cancellation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA.","DOI":"10.1109\/WACV51458.2022.00106"},{"key":"ref_33","unstructured":"Agirre, E., Cer, D., Diab, M., Gonzalez-Agirre, A., and Guo, W. (2013). SEM 2013 shared task: Semantic textual similarity. Second Joint Conference on Lexical and Computational Semantics, Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity, Atlanta, GA, USA, 13\u201314 June 2013, Association for Computational Linguistics (ACL)."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Agirre, E., Banea, C., Cardie, C., Cer, D.M., Diab, M.T., Gonzalez-Agirre, A., Guo, W., Mihalcea, R., Rigau, G., and Wiebe, J. (2014, January 23\u201324). SemEval-2014 Task 10: Multilingual Semantic Textual Similarity. Proceedings of the SemEval@ COLING Confrerence, Dublin, Ireland.","DOI":"10.3115\/v1\/S14-2010"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Agirre, E., Banea, C., Cardie, C., Cer, D., Diab, M., Gonzalez-Agirre, A., Guo, W., Lopez-Gazpio, I., Maritxalar, M., and Mihalcea, R. (2015, January 4\u20135). Semeval-2015 Task 2: Semantic Textual Similarity, English, Spanish and Pilot on Interpretability. Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), Denver, CO, USA.","DOI":"10.18653\/v1\/S15-2045"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Agirre, E., Banea, C., Cer, D., Diab, M., Gonzalez Agirre, A., Mihalcea, R., Rigau Claramunt, G., and Wiebe, J. (2016, January 16\u201317). Semeval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), San Diego, CA, USA.","DOI":"10.18653\/v1\/S16-1081"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., and Specia, L. (2017, January 3\u20134). Semeval-2017 Task 1: Semantic Textual Similarity-Multilingual and Cross-Lingual Focused Evaluation. Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, BC, Canada.","DOI":"10.18653\/v1\/S17-2001"},{"key":"ref_38","unstructured":"Marelli, M., Menini, S., Baroni, M., Bentivogli, L., Bernardi, R., and Zamparelli, R. (2014, January 26\u201331). A SICK Cure for the Evaluation of Compositional Distributional Semantic Models. Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC\u201914), Reykjavik Iceland."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Pang, B., and Lee, L. (2005, January 25\u201330). Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales. Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL\u203205), Ann Arbor, MI, USA.","DOI":"10.3115\/1219840.1219855"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Hu, M., and Liu, B. (2004, January 22\u201325). Mining and Summarizing Customer Reviews. Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Seattle, WA, USA.","DOI":"10.1145\/1014052.1014073"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/s10579-005-7880-9","article-title":"Annotating expressions of opinions and emotions in language","volume":"39","author":"Wiebe","year":"2005","journal-title":"Lang. Resour. Eval."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C.D., Ng, A.Y., and Potts, C. (2013, January 18\u201321). Recursive Deep Models for Semantic Compositionality over a Sentiment Treebank. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, WA, USA.","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Voorhees, E.M., and Tice, D.M. (2000, January 24\u201328). Building a Question Answering Test Collection. Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Athens, Greece.","DOI":"10.1145\/345508.345577"},{"key":"ref_44","unstructured":"Conneau, A., and Kiela, D. (2018, January 7\u201312). Senteval: An Evaluation Toolkit for Universal Sentence Representations. Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan."},{"key":"ref_45","unstructured":"Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., and Garnett, R. PyTorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems, Proceedings of the Annual Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, BC, Canada, 8\u201314 December 2019, Curran Associates, Inc."},{"key":"ref_46","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, Proceedings of the 2017 Conference on Neural Information Processing Systems, Long Beach, CA, USA, 4\u20139 December 2017, Curran Associates, Inc."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Cer, D., Yang, Y., Kong, S.Y., Hua, N., Limtiaco, N., John, R.S., Constant, N., Guajardo-Cespedes, M., Yuan, S., and Tar, C. (November, January 31). Universal Sentence Encoder for English. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, Brussels, Belgium.","DOI":"10.18653\/v1\/D18-2029"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/5\/646\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:21:26Z","timestamp":1760030486000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/5\/646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":47,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["sym17050646"],"URL":"https:\/\/doi.org\/10.3390\/sym17050646","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,25]]}}}