Elamur Research⌕
☰
home / papers / 2026 / Negative Sampling Techniques in Dense Retrieval: A Survey

Negative Sampling Techniques in Dense Retrieval: A Survey

Paper · 2026 · Laurin Wischounig, Abdelrahman Abdallah and Adam Jatowt

Summary

Dense retrievers are usually trained with contrastive objectives such as InfoNCE. Their quality depends heavily on which irrelevant passages, or negatives, the model is shown. This survey reviews 35 key papers on choosing those negatives for dense retrieval in NLP settings like RAG, question answering and dialogue. Unlike earlier reviews, it covers newer methods driven by Large Language Models.

The authors propose a taxonomy with two branches:

  • Sampling strategies: random and in-batch negatives, static hard-negative mining (e.g., BM25), dynamic mining that refreshes negatives during training, cluster-based selection, and methods that detect or avoid false negatives.
  • Data-centric approaches: LLM-generated synthetic data and denoising of mined negatives.

They weigh each family by effectiveness, compute cost and implementation effort, using reported results on MS MARCO, Natural Questions, BEIR and MTEB. They argue that the techniques are largely orthogonal and can be stacked, as top embedding models already do. As a future direction, they suggest generating synthetic negatives dynamically during training, possibly combined with curriculum learning. They also suggest releasing reusable synthetic datasets, which could especially help low-resource languages and domains.

Key points

  • On MS MARCO, MRR@10 rises from 0.261 with in-batch negatives to 0.299 with static BM25 hard negatives, and to 0.330 with ANCE's dynamic mining.
  • Citing RocketQA, the survey notes that about 70% of top-retrieved unlabeled passages may actually be relevant. Without mitigation, such false negatives can lower performance by roughly 10–15%.
  • Cost trade-offs:
    • Static hard negatives give about 6–7% MRR@10 gain for about 33% more training time.
    • Dynamic mining costs about 3× for a 26.4% gain.
    • Dynamic mining plus denoising generally costs 3–5× for 26–42% gains.
  • On MTEB, the leaders are NV-Embed-v2 (69.32) and Gemini Embeddings (66.31). All top-5 models combine several negative sampling techniques. Gemini Embeddings uses a staged pipeline: static mining, then dynamic mining, then LLM denoising, then synthetic data.
  • Scope is limited to contrastive negative sampling. ColBERT-style late interaction and knowledge distillation are treated as complementary techniques. The paper does not run its own standardized benchmark of all methods.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Universität InnsbruckInnsbruck · Austria10 works · 876 citations

 Fields, topics and concepts

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksArts and Humanities · 17,450 worksLanguage and Linguistics · 17,296 worksComputer Vision and Pattern Recognition · 3,486 worksInformation Systems · 1,730 works

🧭 Topics 1Research subjects and languages the work is about.Information retrieval & search · 552 works

Cite

Cite as Laurin Wischounig, Abdelrahman Abdallah and Adam Jatowt. 2026. Negative Sampling Techniques in Dense Retrieval: A Survey. Findings of the Association for Computational Linguistics: EACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-eacl.157

@inproceedings{wischounig2026negative,
  title = {{Negative Sampling Techniques in Dense Retrieval: A Survey}},
  author = {Laurin Wischounig, Abdelrahman Abdallah and Adam Jatowt},
  booktitle = {Findings of the Association for Computational Linguistics: EACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-eacl.157},
  url = {https://doi.org/10.18653/v1/2026.findings-eacl.157}
}

References

75 references, 24 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abdelrahman Abdallah, Mahmoud Abdalla, Bhawna Piryani, Jamshid Mozafari, Mohammed Ali, and Adam Jatowt. 2025a. Rerankarena: A unified platform for evaluating retrieval, reranking and rag with human and llm feedback. In Proceedings of the 34th ACM International Conference on Information and Knowledge… find
  2. Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, Mohammed Ali, and Adam Jatowt. 2025b. Rankify: A comprehensive python toolkit for retrieval, re-ranking, and retrieval-augmented generation. arXiv preprint arXiv:2502.02464. find
  3. Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, and Adam Jatowt. 2025c. Asrank: Zero-shot re-ranking with answer scent for document retrieval. arXiv preprint arXiv:2501.15245. find
  4. Abdelrahman Abdallah, Jamshid Mozafari, Bhawna Piryani, and Adam Jatowt. 2025d. DeAR: Dual-stage document reranking with reasoning agents via LLM distillation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 5710– 5723, Suzhou, China. Association for Computational Lin… find
  5. Abdelrahman Abdallah, Bhawna Piryani, Jonas Wallat, Avishek Anand, and Adam Jatowt. 2025e. Tempretriever: Fusion-based temporal dense passage retrieval for time-sensitive questions. arXiv preprint arXiv:2502.21024. — [arXiv:2502.21024](https://arxiv.org/abs/2502.21024) find
  6. Abhijit Anand, Jurek Leonhardt, Jaspreet Singh, Koustav Rudra, and Avishek Anand. 2023. Data augmentation for sample efficient and robust document ranking. Preprint, arXiv:2311.15426. — [arXiv:2311.15426](https://arxiv.org/abs/2311.15426) find
  7. Ingeol Baek, Jimin Lee, Joonho Yang, and Hwanhee Lee. 2024. Crafting the path: Robust query rewriting for information retrieval. Preprint, arXiv:2407.12529. — [arXiv:2407.12529](https://arxiv.org/abs/2407.12529) find
  8. R Ricardo Baeza-Yates, Berthier Ribeiro-Neto, and 1 others. 1999. Modern information retrieval. ACM Press. find
  9. Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, Mir Rosenberg, Xia Song, Alina Stoica, Saurabh Tiwary, and Tong Wang. 2018. Ms marco: A human generated machine reading comprehension dataset. Preprint, arXiv:…
  10. Payal Bajaj, Daniel Campos, Nick Craswell, Li Deng, Jianfeng Gao, Xiaodong Liu, Rangan Majumder, Andrew McNamara, Bhaskar Mitra, Tri Nguyen, and 1 others. 2016. Ms marco: A human generated machine reading comprehension dataset. arXiv preprint arXiv:1611.09268.
  11. Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. Preprint, arXiv:2002.05709.
  12. Xilun Chen, Kushal Lakhotia, Barlas Oğuz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, and Wen-tau Yih. 2021. Salient phrase aware dense retrieval: Can a dense retriever imitate a sparse one? arXiv preprint arXiv:2110.06918. find
  13. Zesen Cheng, Hang Zhang, Kehan Li, Sicong Leng, Zhiqiang Hu, Fei Wu, Deli Zhao, Xin Li, and Lidong Bing. 2024. Breaking the memory barrier: Near infinite batch size scaling for contrastive loss. arXiv preprint arXiv:2410.17243. find
  14. Nachshon Cohen, Hedda Cohen Indelman, Yaron Fairstein, and Guy Kushilevitz. 2024. Indi: Informative and diverse sampling for dense retrieval. find
  15. Zhuyun Dai, Vincent Y. Zhao, Ji Ma, Yi Luan, Jianmo Ni, Jing Lu, Anton Bakalov, Kelvin Guu, Keith B. Hall, and Ming-Wei Chang. 2022. Promptagator: Few-shot dense retrieval from 8 examples. Preprint, arXiv:2209.11755.
  16. Gabriel de Souza P. Moreira, Radek Osmulski, Mengyao Xu, Ronay Ak, Benedikt Schifferer, and Even Oldridge. 2025. Nv-retriever: Improving text embedding models with effective hard-negative mining. Preprint, arXiv:2407.15831. — [arXiv:2407.15831](https://arxiv.org/abs/2407.15831) find
  17. Saumya Gandhi, Ritu Gala, Vijay Viswanathan, Tongshuang Wu, and Graham Neubig. 2024. Better synthetic data by retrieving and transforming existing datasets. Preprint, arXiv:2404.14361. find
  18. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2022a. Precise zero-shot dense retrieval without relevance labels. Preprint, arXiv:2212.10496.
  19. Luyu Gao, Xueguang Ma, Jimmy Lin, and Jamie Callan. 2022b. Tevatron: An efficient and flexible toolkit for dense retrieval. Preprint, arXiv:2203.05765. find
  20. Luyu Gao, Yunyi Zhang, Jiawei Han, and Jamie Callan. 2021. Scaling deep contrastive learning batch size under memory limited setup. arXiv preprint arXiv:2101.06983.
  21. Raphael Gruber, Abdelrahman Abdallah, Michael Färber, and Adam Jatowt. 2025. ComplexTempQA: A 100m dataset for complex temporal question answering. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 9100–9112, Suzhou, China. Association for Computational… find
  22. Sebastian Hofstätter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, and Allan Hanbury. 2021. Efficiently teaching an effective dense retriever with balanced topic aware sampling. Preprint, arXiv:2104.06967.
  23. Xinshuo Hu, Zifei Shan, Xinping Zhao, Zetian Sun, Zhenyu Liu, Dongfang Li, Shaolin Ye, Xinyuan Wei, Qian Chen, Baotian Hu, Haofen Wang, Jun Yu, and Min Zhang. 2025. Kalm-embedding: Superior training data brings a stronger embedding model. Preprint, arXiv:2501.01028. — [arXiv:2501.01028](https://arxiv.org/abs/2501.01028) find
  24. Yifan Ji, Zhipeng Xu, Zhenghao Liu, Yukun Yan, Shi Yu, Yishan Li, Zhiyuan Liu, Yu Gu, Ge Yu, and Maosong Sun. 2025. Learning more effective representations for dense retrieval through deliberate thinking before search. Preprint, arXiv:2502.12974. — [arXiv:2502.12974](https://arxiv.org/abs/2502.12974) find
  25. Vladimir Karpukhin, Barlas Oguz, Sewon Chen, Patrick Lischinski, Armand Joulin, and Edouard Grave. 2020a. Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
  26. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020b. Dense passage retrieval for open-domain question answering. In EMNLP (1), pages 6769–6781.
  27. Omar Khattab and Matei Zaharia. 2020. Colbert: Efficient and effective passage search via contextualized late interaction over bert. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ’20).
  28. Jinhyuk Lee, Feiyang Chen, Sahil Dua, Daniel Cer, Madhuri Shanbhogue, Iftekhar Naim, Gustavo Hernández Ábrego, Zhe Li, Kaifeng Chen, Henrique Schechter Vera, Xiaoqi Ren, Shanfeng Zhang, Daniel Salz, Michael Boratko, Jay Han, Blair Chen, Shuo Huang, Vikram Rao, Paul Suganthan, and 28 others. 2025. Ge… — Gemini Embedding: Generalizable Embeddings from Gemini
  29. Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R. Cole, Kai Hui, Michael Boratko, Rajvi Kapadia, Wen Ding, Yi Luan, Sai Meher Karthik Duddu, Gustavo Hernandez Abrego, Weiqiang Shi, Nithi Gupta, Aditya Kusupati, Prateek Jain, Siddhartha Reddy Jonnalagadda, Ming-Wei Chang, and Ift… — Gecko: Versatile Text Embeddings Distilled from Large Language Models
  30. Minghan Li and Eric Gaussier. 2024. Domain adaptation for dense retrieval and conversational dense retrieval through self-supervision by meticulous pseudo-relevance labeling. arXiv preprint arXiv:2403.08970. find
  31. Shiyu Li, Yang Tang, Shizhe Chen, and Xi Chen. 2024a. Conan-embedding: General text embedding with more and better negative samples. Preprint, arXiv:2408.15710. find
  32. Xiaopeng Li, Xiangyang Li, Hao Zhang, Zhaocheng Du, Pengyue Jia, Yichao Wang, Xiangyu Zhao, Huifeng Guo, and Ruiming Tang. 2024b. Syneg: Llm-driven synthetic hard-negatives for dense retrieval. Preprint, arXiv:2412.17250. — [arXiv:2412.17250](https://arxiv.org/abs/2412.17250) find
  33. Sheng-Chieh Lin, Jheng-Hong Yang, Min-Yen Chen, and Jimmy Lin. 2023. How to train your dragon: Diverse augmentation towards generalizable dense retrieval. arXiv preprint arXiv:2302.07452.
  34. Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. 2021a. In-batch negatives for knowledge distillation with tightly-coupled teachers for dense retrieval. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 163–173. setting. In Proceedings of the 47th Internati… find
  35. Nils Reimers and Iryna Gurevych. 2019. Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084.
  36. Ruiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, Qiaoqiao She, Hua Wu, Haifeng Wang, and Ji-Rong Wen. 2021. Rocketqav2: A joint training method for dense passage retrieval and passage re-ranking. arXiv preprint arXiv:2110.07367.
  37. Sheng-Chieh Lin, Jheng-Hong Yang, and Jimmy Lin. 2021b. In-batch negatives for knowledge distillation with tightly-coupled teachers for dense retrieval. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021). find
  38. Stephen Robertson, Hugo Zaragoza, and 1 others. 2009. The probabilistic relevance framework: Bm25 and beyond. Foundations and Trends® in Information Retrieval, 3(4):333–389. find
  39. Erik Lindgren, Sashank Reddi, Ruiqi Guo, and Sanjiv Kumar. 2021a. Efficient training of retrieval models using negative cache. Advances in Neural Information Processing Systems, 34:4134–4146. find
  40. Keshav Santhanam, Omar Khattab, Christopher Potts, and Matei Zaharia. 2022. Plaid: an efficient engine for late interaction retrieval. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, pages 1747–1756. find
  41. Erik Lindgren, Sashank Reddi, Ruiqi Guo, and Sanjiv Kumar. 2021b. Efficient training of retrieval models using negative cache. In Advances in Neural Information Processing Systems, volume 34, pages 4134–4146. Curran Associates, Inc. find
  42. Christopher Sciavolino, Zexuan Zhong, Jinhyuk Lee, and Danqi Chen. 2021. Simple entity-centric questions challenge dense retrievers. arXiv preprint arXiv:2109.08535.
  43. Siladittya Manna, Soumitri Chattopadhyay, Rakesh Dey, Umapada Pal, and Saumik Bhattacharya. 2025. Dynamically scaled temperature in self-supervised contrastive learning. IEEE Transactions on Artificial Intelligence. find
  44. Tianhao Shen, Mingtong Liu, Ming Zhou, and Deyi Xiong. 2022. Recovering gold from black sand: Multilingual dense passage retrieval with hard and false negative samples. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10659–10670, Abu Dhabi, United Ara… find
  45. Hansa Meghwani, Amit Agarwal, Priyaranjan Pattnayak, Hitesh Laxmichand Patel, and Srikant Panda. 2025. Hard negative mining for domain-specific retrieval in enterprise systems. Preprint, arXiv:2505.18366. find
  46. Niklas Muennighoff, Nouamane Tazi, Loïc Magne, and Nils Reimers. 2023. Mteb: Massive text embedding benchmark. Preprint, arXiv:2210.07316.
  47. Thanh-Do Nguyen, Chi Minh Bui, and Xuan-Hieu Phan. 2023. Passage-based bm25 hard negatives: A simple and effective negative sampling strategy for dense retrieval. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation (PACLIC 2023). find
  48. Yingqi Qu, Yuchen Ding, Jing Liu, Kai Liu, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu, and Haifeng Wang. 2021. Rocketqa: An optimized training approach to dense passage retrieval for open-domain question answering. Preprint, arXiv:2010.08191.
  49. Thilina Chaturanga Rajapakse, Andrew Yates, and Maarten de Rijke. 2024. Negative sampling techniques for dense passage retrieval in a multilingual Aarush Sinha. 2025. Don’t retrieve, generate: Prompting llms for synthetic training data in dense retrieval. Preprint, arXiv:2504.21015. — [arXiv:2504.21015](https://arxiv.org/abs/2504.21015) find
  50. Aivin V. Solatorio. 2024. Gistembed: Guided in-sample selection of training negatives for text embedding fine-tuning. Preprint, arXiv:2402.16829. — [arXiv:2402.16829](https://arxiv.org/abs/2402.16829) find
  51. Si Sun, Chenyan Xiong, Yue Yu, Arnold Overwijk, Zhiyuan Liu, and Jie Bao. 2022. Reduce catastrophic forgetting of dense retrieval training with teleportation negatives. Preprint, arXiv:2210.17167. find
  52. Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh, and Jimmy Lin. 2025. Conventional contrastive learning often falls short: Improving dense retrieval with cross-encoder listwise distillation and synthetic data. Preprint, arXiv:2505.19274. — [arXiv:2505.19274](https://arxiv.org/abs/2505.19274) find
  53. Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. 2021a. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663.
  54. Nandan Thakur, Nils Reimers, Andreas Rücklé, Abhishek Srivastava, and Iryna Gurevych. 2021b. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. Preprint, arXiv:2104.08663.
  55. Nandan Thakur, Crystina Zhang, Xueguang Ma, and Jimmy Lin. 2025. Fixing data that hurts performance: Cascading llms to relabel hard negatives for robust information retrieval. Preprint, arXiv:2505.16967. — [arXiv:2505.16967](https://arxiv.org/abs/2505.16967) find
  56. Aaron van den Oord, Yazhe Li, and Oriol Vinyals. 2019. Representation learning with contrastive predictive coding. Preprint, arXiv:1807.03748.
  57. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, and Furu Wei. 2024a. Improving text embeddings with large language models. Preprint, arXiv:2401.00368.
  58. Shiqi Wang, Yeqin Zhang, and Cam-Tu Nguyen. 2024b. Mitigating the impact of false negatives in dense retrieval with contrastive confidence regularization. Preprint, arXiv:2401.00165. — [arXiv:2401.00165](https://arxiv.org/abs/2401.00165) find
  59. Haoyang Wen, Jiang Guo, Yi Zhang, Jiarong Jiang, and Zhiguo Wang. 2025. On synthetic data strategies for domain-specific generative retrieval. Preprint, arXiv:2502.17957. find
  60. Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk. 2020. Approximate nearest neighbor negative contrastive learning for dense text retrieval. Preprint, arXiv:2007.00808.
  61. Lanling Xu, Jianhai Luo, and Jianhua Li. 2022. Negative sampling for contrastive representation learning: A review. arXiv preprint arXiv:2206.00212. — [arXiv:2206.00212](https://arxiv.org/abs/2206.00212) find
  62. Zhen Yang, Ming Ding, Tinglin Huang, Yukuo Cen, Junshuai Song, Bin Xu, Yuxiao Dong, and Jie Tang. 2024a. Does negative sampling matter? a review with insights into its theory and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8):5692–5711. find
  63. Zhen Yang, Haochen Ma, Xin Sun, Jian-Yun Yu, Jiajie Lin, Hongtao Chen, Zicong Song, and Ji-Rong Wen. 2024b. Does negative sampling matter? a review with insights into its theory and applications. IEEE Transactions on Pattern Analysis and Machine Intelligence. find
  64. Zhen Yang, Zhou Shao, Yuxiao Dong, and Jie Tang. 2024c. Trisampler: A better negative sampling principle for dense retrieval. Preprint, arXiv:2402.11855. — [arXiv:2402.11855](https://arxiv.org/abs/2402.11855) find
  65. Sizhe Yuen, Ting Su, Ziyang Wang, Yali Du, and Adam J. Sobey. 2025. Automatic dataset generation for knowledge intensive question answering tasks. Preprint, arXiv:2505.14212. — [arXiv:2505.14212](https://arxiv.org/abs/2505.14212) find
  66. Goksenin Yuksel, David Rau, and Jaap Kamps. 2025. Remining hard negatives for generative pseudo labeled domain adaptation. Preprint, arXiv:2501.14434. — [arXiv:2501.14434](https://arxiv.org/abs/2501.14434) find
  67. George Zerveas, Navid Rekabsaz, and Carsten Eickhoff. 2023. Enhancing the ranking context of dense retrieval methods through reciprocal nearest neighbors. Preprint, arXiv:2305.15720. — [arXiv:2305.15720](https://arxiv.org/abs/2305.15720) find
  68. Jingtao Zhan, Jiaxin Dai, Yizhen Ding, Yujie Huang, Weijiang Liu, Shujian Chu, Yi Wang, Daxin Huang, and Yunjie Zhou. 2021a. Optimizing dense retrieval model training with hard negatives. In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retriev… find
  69. Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Jiafeng Guo, Min Zhang, and Shaoping Ma. 2021b. Optimizing dense retrieval model training with hard negatives. In Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pages 1503–1512. find
  70. Jingtao Zhan, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 2020. Learning to retrieve: How to train a dense retrieval model effectively and efficiently. arXiv preprint arXiv:2010.10469. — [arXiv:2010.10469](https://arxiv.org/abs/2010.10469) find
  71. Chu Zhao, Enneng Yang, Yuting Liu, Jianzhe Zhao, Guibing Guo, and Xingwei Wang. 2025. Can llm-driven hard negative sampling empower collaborative filtering? findings and potentials. arXiv preprint arXiv:2504.04726. — [arXiv:2504.04726](https://arxiv.org/abs/2504.04726) find
  72. Wayne Xin Zhao, Jing Liu, Ruiyang Ren, and Ji-Rong Wen. 2024. Dense text retrieval based on pretrained language models: A survey. ACM Transactions on Information Systems, 42(4):1–60. find
  73. Kun Zhou, Yu Fu, Guangwei Luo, Huazheng Zhu, Yifan Chen, Xiangbo Shi, Hongwei Zhou, Yang Zhang, and Jun Guan. 2022. Simans: Simple ambiguous negatives sampling for dense text retrieval. arXiv preprint arXiv:2210.11773. find
  74. Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Haonan Chen, Zhicheng Dou, and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey. CoRR, abs/2308.07107.
  75. Shengyao Zhuang, Houxing Ren, Linjun Shou, Jian Pei, Ming Gong, Guido Zuccon, and Daxin Jiang. 2023. Bridging the gap between indexing and retrieval for differentiable search index with query generation. Preprint, arXiv:2206.10128. — [arXiv:2206.10128](https://arxiv.org/abs/2206.10128) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wischounig-2026-negative-sampling-techniques-dense-retrieval/