{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:13:36Z","timestamp":1783696416053,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,20]]},"DOI":"10.1145\/3805712.3809628","type":"proceedings-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:28:19Z","timestamp":1783693699000},"page":"213-222","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8644-9209","authenticated-orcid":false,"given":"Hyewon","family":"Choi","sequence":"first","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4062-6389","authenticated-orcid":false,"given":"Jooyoung","family":"Choi","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5581-6827","authenticated-orcid":false,"given":"Hansol","family":"Jang","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9339-0566","authenticated-orcid":false,"given":"Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0800-9160","authenticated-orcid":false,"given":"Chulmin","family":"Yun","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2595-2887","authenticated-orcid":false,"given":"Changwook","family":"Jun","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0297-4269","authenticated-orcid":false,"given":"Stanley Jungkyu","family":"Choi","sequence":"additional","affiliation":[{"name":"LG AI Research, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144","author":"Bonifacio Luiz","year":"2022","unstructured":"Luiz Bonifacio, Hugo Abonizio, Marzieh Fadaee, and Rodrigo Nogueira. 2022. Inpars: Data augmentation for information retrieval using large language models. arXiv preprint arXiv:2202.05144 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557343"},{"key":"e_1_3_2_1_3_1","unstructured":"Devendra Singh Chaplot. 2023. Albert q. jiang alexandre sablayrolles arthur mensch chris bamford devendra singh chaplot diego de las casas florian bressand gianna lengyel guillaume lample lucile saulnier l\u00e9lio renard lavaud marie-anne lachaux pierre stock teven le scao thibaut lavril thomas wang timoth\u00e9e lacroix william el sayed. arXiv preprint arXiv:2310.06825 Vol. 3 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Honglak Lee, and Chulmin Yun.","author":"Choi Jooyoung","year":"2025","unstructured":"Jooyoung Choi, Hyun Kim, Hansol Jang, Changwook Jun, Kyunghoon Bae, Hyewon Choi, Stanley Jungkyu Choi, Honglak Lee, and Chulmin Yun. 2025. LG-ANNA-Embedding technical report. arXiv preprint arXiv:2506.07438 (2025)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56063-7_16"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657834"},{"key":"e_1_3_2_1_7_1","volume-title":"Promptagator: Few-shot dense retrieval from 8 examples. arXiv preprint arXiv:2209.11755","author":"Dai Zhuyun","year":"2022","unstructured":"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. arXiv preprint arXiv:2209.11755 (2022)."},{"key":"e_1_3_2_1_8_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_9_1","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2022. Lora: Low-rank adaptation of large language models. ICLR, Vol. 1, 2 (2022), 3.","journal-title":"ICLR"},{"key":"e_1_3_2_1_10_1","volume-title":"Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118","author":"Izacard Gautier","year":"2021","unstructured":"Gautier Izacard, Mathilde Caron, Lucas Hosseini, Sebastian Riedel, Piotr Bojanowski, Armand Joulin, and Edouard Grave. 2021. Unsupervised dense information retrieval with contrastive learning. arXiv preprint arXiv:2112.09118 (2021)."},{"key":"e_1_3_2_1_11_1","volume-title":"Noisy self-training with synthetic queries for dense retrieval. arXiv preprint arXiv:2311.15563","author":"Jiang Fan","year":"2023","unstructured":"Fan Jiang, Tom Drummond, and Trevor Cohn. 2023. Noisy self-training with synthetic queries for dense retrieval. arXiv preprint arXiv:2311.15563 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Noe Pion, Philippe Weinzaepfel, and Diane Larlus.","author":"Kalantidis Yannis","year":"2020","unstructured":"Yannis Kalantidis, Mert Bulent Sariyildiz, Noe Pion, Philippe Weinzaepfel, and Diane Larlus. 2020. Hard negative mixing for contrastive learning. Advances in neural information processing systems, Vol. 33 (2020), 21798-21809."},{"key":"e_1_3_2_1_13_1","volume-title":"Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih.","author":"Karpukhin Vladimir","year":"2020","unstructured":"Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. Dense Passage Retrieval for Open-Domain Question Answering.. In EMNLP (1). 6769-6781."},{"key":"e_1_3_2_1_14_1","volume-title":"Gecko: Versatile text embeddings distilled from large language models. arXiv preprint arXiv:2403.20327","author":"Lee Jinhyuk","year":"2024","unstructured":"Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren, Blair Chen, Daniel Cer, Jeremy R Cole, Kai Hui, Michael Boratko, Rajvi Kapadia, Wen Ding, et al., 2024. Gecko: Versatile text embeddings distilled from large language models. arXiv preprint arXiv:2403.20327 (2024)."},{"key":"e_1_3_2_1_15_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_1_16_1","volume-title":"Making text embedders few-shot learners. arXiv preprint arXiv:2409.15700","author":"Li Chaofan","year":"2024","unstructured":"Chaofan Li, MingHao Qin, Shitao Xiao, Jianlyu Chen, Kun Luo, Yingxia Shao, Defu Lian, and Zheng Liu. 2024. Making text embedders few-shot learners. arXiv preprint arXiv:2409.15700 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"NV-Retriever: Improving text embedding models with effective hard-negative mining. arXiv preprint arXiv:2407.15831","author":"Moreira Gabriel","year":"2024","unstructured":"Gabriel de Souza P Moreira, Radek Osmulski, Mengyao Xu, Ronay Ak, Benedikt Schifferer, and Even Oldridge. 2024. NV-Retriever: Improving text embedding models with effective hard-negative mining. arXiv preprint arXiv:2407.15831 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Mitigating false-negative contexts in multi-document question answering with retrieval marginalization. arXiv preprint arXiv:2103.12235","author":"Ni Ansong","year":"2021","unstructured":"Ansong Ni, Matt Gardner, and Pradeep Dasigi. 2021. Mitigating false-negative contexts in multi-document question answering with retrieval marginalization. arXiv preprint arXiv:2103.12235 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.271"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.466"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657854"},{"key":"e_1_3_2_1_22_1","volume-title":"Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. Beir: A heterogenous benchmark for zero-shot evaluation of information retrieval models. arXiv preprint arXiv:2104.08663 (2021)."},{"key":"e_1_3_2_1_23_1","volume-title":"Hard Negatives","author":"Thakur Nandan","year":"2025","unstructured":"Nandan Thakur, Crystina Zhang, and Xueguang Ma Jimmy Lin. 2025. Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs. In Findings of the Association for Computational Linguistics: EMNLP 2025. 9064-9083."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1476"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.642"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29885"},{"key":"e_1_3_2_1_27_1","volume-title":"Approximate nearest neighbor negative contrastive learning for dense text retrieval. arXiv preprint arXiv:2007.00808","author":"Xiong Lee","year":"2020","unstructured":"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. arXiv preprint arXiv:2007.00808 (2020)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Shi-Qi Yan Jia-Chen Gu Yun Zhu and Zhen-Hua Ling. 2024. Corrective retrieval augmented generation. (2024).","DOI":"10.2139\/ssrn.5267341"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28779"},{"key":"e_1_3_2_1_30_1","volume-title":"Xin He, and William M Campbell.","author":"Zeng Qiuhai","year":"2024","unstructured":"Qiuhai Zeng, Zimeng Qiu, Dae Yon Hwang, Xin He, and William M Campbell. 2024. Unsupervised text representation learning via instruction-tuning for zero-shot dense retrieval. arXiv preprint arXiv:2409.16497 (2024)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462880"},{"key":"e_1_3_2_1_32_1","volume-title":"Towards understanding retrieval accuracy and prompt quality in rag systems. arXiv preprint arXiv:2411.19463","author":"Zhao Shengming","year":"2024","unstructured":"Shengming Zhao, Yuheng Huang, Jiayang Song, Zhijie Wang, Chengcheng Wan, and Lei Ma. 2024a. Towards understanding retrieval accuracy and prompt quality in rag systems. arXiv preprint arXiv:2411.19463 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637870"}],"event":{"name":"SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Melbourne VIC Australia","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:30:39Z","timestamp":1783693839000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805712.3809628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":33,"alternative-id":["10.1145\/3805712.3809628","10.1145\/3805712"],"URL":"https:\/\/doi.org\/10.1145\/3805712.3809628","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}