{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T02:14:39Z","timestamp":1783390479726,"version":"3.54.6"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032295316","type":"print"},{"value":"9783032295323","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T00:00:00Z","timestamp":1783123200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2027]]},"DOI":"10.1007\/978-3-032-29532-3_17","type":"book-chapter","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T08:52:04Z","timestamp":1783068724000},"page":"237-251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evaluating Noisy Optimization in\u00a0Finetuning LMs for\u00a0Neural Ranking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5324-4952","authenticated-orcid":false,"given":"Daniel","family":"Vollmers","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8515-5253","authenticated-orcid":false,"given":"Arnab","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7112-3516","authenticated-orcid":false,"given":"Axel-Cyrille","family":"Ngonga Ngomo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,4]]},"reference":[{"key":"17_CR1","unstructured":"Agarwal, O., Bikel, D.M.: Entity linking via dual and cross-attention encoders. CoRR abs\/2004.03555 (2020). https:\/\/arxiv.org\/abs\/2004.03555"},{"key":"17_CR2","unstructured":"Arpit, D., et al.: A closer look at memorization in deep networks. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, ICML 2017, Sydney, NSW, Australia, 6\u201311 August 2017. Proceedings of Machine Learning Research, vol.\u00a070, pp. 233\u2013242. PMLR (2017). http:\/\/proceedings.mlr.press\/v70\/arpit17a.html"},{"key":"17_CR3","unstructured":"Blanc, G., Gupta, N., Valiant, G., Valiant, P.: Implicit regularization for deep neural networks driven by an Ornstein-Uhlenbeck like process. In: Conference on Learning Theory, COLT 2020. Proceedings of Machine Learning Research, vol.\u00a0125, pp. 483\u2013513. PMLR (2020). http:\/\/proceedings.mlr.press\/v125\/blanc20a.html"},{"key":"17_CR4","unstructured":"Bradley, A.V., Gomez-Uribe, C.A.: How can increased randomness in stochastic gradient descent improve generalization? CoRR abs\/2108.09507 (2021). https:\/\/arxiv.org\/abs\/2108.09507"},{"key":"17_CR5","doi-asserted-by":"publisher","unstructured":"D\u00e9jean, H., Clinchant, S., Formal, T.: A thorough comparison of cross-encoders and LLMs for reranking SPLADE. CoRR abs\/2403.10407 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2403.10407","DOI":"10.48550\/ARXIV.2403.10407"},{"key":"17_CR6","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: 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, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/n19-1423","DOI":"10.18653\/v1\/n19-1423"},{"issue":"2","key":"17_CR7","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TBDATA.2025.3618474","volume":"12","author":"M Douze","year":"2026","unstructured":"Douze, M., et al.: The Faiss library. IEEE Trans. Big Data 12(2), 346\u2013361 (2026). https:\/\/doi.org\/10.1109\/TBDATA.2025.3618474","journal-title":"IEEE Trans. Big Data"},{"key":"17_CR8","doi-asserted-by":"publisher","unstructured":"Fang, Z., Cao, Y., Li, Q., Zhang, D., Zhang, Z., Liu, Y.: Joint entity linking with deep reinforcement learning. In: The World Wide Web Conference, WWW 2019, San Francisco, CA, USA, 13\u201317 May 2019, pp. 438\u2013447. ACM (2019). https:\/\/doi.org\/10.1145\/3308558.3313517","DOI":"10.1145\/3308558.3313517"},{"key":"17_CR9","doi-asserted-by":"publisher","unstructured":"Ganea, O., Hofmann, T.: Deep joint entity disambiguation with local neural attention. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, EMNLP 2017, Copenhagen, Denmark, 9\u201311 September 2017, pp. 2619\u20132629. Association for Computational Linguistics (2017). https:\/\/doi.org\/10.18653\/v1\/d17-1277","DOI":"10.18653\/v1\/d17-1277"},{"key":"17_CR10","doi-asserted-by":"publisher","unstructured":"Guo, J., Fan, Y., Ai, Q., Croft, W.B.: A deep relevance matching model for ad-hoc retrieval. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, CIKM 2016, pp. 55\u201364. Association for Computing Machinery, New York (2016). https:\/\/doi.org\/10.1145\/2983323.2983769","DOI":"10.1145\/2983323.2983769"},{"key":"17_CR11","unstructured":"HaoChen, J.Z., Wei, C., Lee, J.D., Ma, T.: Shape matters: understanding the implicit bias of the noise covariance. In: Conference on Learning Theory, COLT 2021, Boulder, Colorado, USA, 15\u201319 August 2021. Proceedings of Machine Learning Research, vol.\u00a0134, pp. 2315\u20132357. PMLR (2021). http:\/\/proceedings.mlr.press\/v134\/haochen21a.html"},{"key":"17_CR12","unstructured":"Jin, C., Ge, R., Netrapalli, P., Kakade, S.M., Jordan, M.I.: How to escape saddle points efficiently. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol.\u00a070, pp. 1724\u20131732. PMLR (2017). http:\/\/proceedings.mlr.press\/v70\/jin17a.html"},{"key":"17_CR13","doi-asserted-by":"publisher","unstructured":"Jin, C., Netrapalli, P., Ge, R., Kakade, S.M., Jordan, M.I.: On nonconvex optimization for machine learning: gradients, stochasticity, and saddle points. J. ACM 68(2) (2021). https:\/\/doi.org\/10.1145\/3418526","DOI":"10.1145\/3418526"},{"key":"17_CR14","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7\u20139 May 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"17_CR15","unstructured":"Kunstner, F., Milligan, A., Yadav, R., Schmidt, M., Bietti, A.: Heavy-tailed class imbalance and why adam outperforms gradient descent on language models. In: Globersons, A., et al. (eds.) Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024, Vancouver, BC, Canada, 10\u201315 December 2024 (2024). http:\/\/papers.nips.cc\/paper_files\/paper\/2024\/hash\/350e718ff74062b4bac2c6ffd9e1ac66-Abstract-Conference.html"},{"key":"17_CR16","doi-asserted-by":"publisher","unstructured":"Lehmann, E.L.: Introduction to Student (1908) The Probable Error of a Mean, pp. 29\u201332. Springer, New York (1992). https:\/\/doi.org\/10.1007\/978-1-4612-4380-9_3","DOI":"10.1007\/978-1-4612-4380-9_3"},{"key":"17_CR17","doi-asserted-by":"publisher","unstructured":"Liu, G., Xue, Z., Zhang, X., Johnson, K.M., Wang, R.: Pac-tuning: fine-tuning pre-trained language models with PAC-driven perturbed gradient descent. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, EMNLP, pp. 12178\u201312189. Association for Computational Linguistics (2023). https:\/\/doi.org\/10.18653\/v1\/2023.emnlp-main.748","DOI":"10.18653\/v1\/2023.emnlp-main.748"},{"key":"17_CR18","unstructured":"Liu, T., Li, Y., Wei, S., Zhou, E., Zhao, T.: Noisy gradient descent converges to flat minima for nonconvex matrix factorization. In: The 24th International Conference on Artificial Intelligence and Statistics, AISTATS. Proceedings of Machine Learning Research, vol.\u00a0130, pp. 1891\u20131899. PMLR (2021). http:\/\/proceedings.mlr.press\/v130\/liu21e.html"},{"key":"17_CR19","unstructured":"Nogueira, R.F., Cho, K.: Passage re-ranking with BERT. CoRR abs\/1901.04085 (2019). http:\/\/arxiv.org\/abs\/1901.04085"},{"key":"17_CR20","unstructured":"Orvieto, A., Kersting, H., Proske, F., Bach, F.R., Lucchi, A.: Anticorrelated noise injection for improved generalization. In: International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol.\u00a0162, pp. 17094\u201317116. PMLR (2022). https:\/\/proceedings.mlr.press\/v162\/orvieto22a.html"},{"key":"17_CR21","unstructured":"Orvieto, A., Raj, A., Kersting, H., Bach, F.R.: Explicit regularization in overparametrized models via noise injection. In: Ruiz, F.J.R., Dy, J.G., van\u00a0de Meent, J. (eds.) International Conference on Artificial Intelligence and Statistics, Palau de Congressos, Valencia, Spain, 25\u201327 April 2023. Proceedings of Machine Learning Research, vol.\u00a0206, pp. 7265\u20137287. PMLR (2023). https:\/\/proceedings.mlr.press\/v206\/orvieto23a.html"},{"key":"17_CR22","doi-asserted-by":"publisher","unstructured":"Patrini, G., Rozza, A., Menon, A.K., Nock, R., Qu, L.: Making deep neural networks robust to label noise: a loss correction approach. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 2233\u20132241. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.240","DOI":"10.1109\/CVPR.2017.240"},{"issue":"2","key":"17_CR23","first-page":"45","volume":"26","author":"BT Polyak","year":"1990","unstructured":"Polyak, B.T., Tsybakov, A.B.: Optimal order of accuracy of search algorithms in stochastic optimization. Problemy Peredachi Informatsii 26(2), 45\u201353 (1990)","journal-title":"Problemy Peredachi Informatsii"},{"key":"17_CR24","doi-asserted-by":"publisher","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using Siamese BERT-networks. In: Inui, K., Jiang, J., Ng, V., Wan, X. (eds.) 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, China, 3\u20137 November 2019, pp. 3980\u20133990. Association for Computational Linguistics (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1410","DOI":"10.18653\/v1\/D19-1410"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat., 400\u2013407 (1951)","DOI":"10.1214\/aoms\/1177729586"},{"key":"17_CR26","doi-asserted-by":"publisher","unstructured":"Shoshan, E., Radinsky, K.: Latent entities extraction: how to extract entities that do not appear in the text? In: Korhonen, A., Titov, I. (eds.) Proceedings of the 22nd Conference on Computational Natural Language Learning, Brussels, Belgium, pp. 200\u2013210. Association for Computational Linguistics (2018). https:\/\/doi.org\/10.18653\/v1\/K18-1020. https:\/\/aclanthology.org\/K18-1020\/","DOI":"10.18653\/v1\/K18-1020"},{"key":"17_CR27","doi-asserted-by":"publisher","unstructured":"Sil, A., Kundu, G., Florian, R., Hamza, W.: Neural cross-lingual entity linking. In: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, 2\u20137 February 2018, pp. 5464\u20135472. AAAI Press (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.11964","DOI":"10.1609\/aaai.v32i1.11964"},{"key":"17_CR28","unstructured":"Smith, S.L., Elsen, E., De, S.: On the generalization benefit of noise in stochastic gradient descent. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020. Proceedings of Machine Learning Research (2020). http:\/\/proceedings.mlr.press\/v119\/smith20a.html"},{"issue":"6","key":"17_CR29","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/s10791-021-09398-0","volume":"24","author":"M Trabelsi","year":"2021","unstructured":"Trabelsi, M., Chen, Z., Davison, B.D., Heflin, J.: Neural ranking models for document retrieval. Inform. Retr. J. 24(6), 400\u2013444 (2021). https:\/\/doi.org\/10.1007\/s10791-021-09398-0","journal-title":"Inform. Retr. J."},{"key":"17_CR30","doi-asserted-by":"publisher","unstructured":"Wang, L., et al.: Text embeddings by weakly-supervised contrastive pre-training. CoRR abs\/2212.03533 (2022). https:\/\/doi.org\/10.48550\/arXiv.2212.03533","DOI":"10.48550\/arXiv.2212.03533"},{"key":"17_CR31","doi-asserted-by":"publisher","unstructured":"Wu, L., Petroni, F., Josifoski, M., Riedel, S., Zettlemoyer, L.: Scalable zero-shot entity linking with dense entity retrieval. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, 16\u201320 November 2020, pp. 6397\u20136407. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.519","DOI":"10.18653\/v1\/2020.emnlp-main.519"},{"key":"17_CR32","doi-asserted-by":"publisher","unstructured":"Yamada, I., Asai, A., Shindo, H., Takeda, H., Matsumoto, Y.: LUKE: deep contextualized entity representations with entity-aware self-attention. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, Online, 16\u201320 November 2020, pp. 6442\u20136454. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.523","DOI":"10.18653\/v1\/2020.emnlp-main.523"},{"key":"17_CR33","unstructured":"Zhang, G., et al.: Which algorithmic choices matter at which batch sizes? Insights from a noisy quadratic model. In: Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems, NeurIPS 2019 (2019). https:\/\/dl.acm.org\/doi\/abs\/10.5555\/3454287.3455023"},{"key":"17_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Sind, X., Liu, T., Fang, Z., Li, Q.: Joint entity linking and relation extraction with neural networks for knowledge base population. In: 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, 19\u201324 July 2020, pp.\u00a01\u20138. IEEE (2020). https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9207021","DOI":"10.1109\/IJCNN48605.2020.9207021"},{"key":"17_CR35","unstructured":"Zhou, M., Liu, T., Li, Y., Lin, D., Zhou, E., Zhao, T.: Toward understanding the importance of noise in training neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, PMLR (2019). http:\/\/proceedings.mlr.press\/v97\/zhou19d.html"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-29532-3_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T01:52:32Z","timestamp":1783389152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-29532-3_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,4]]},"ISBN":["9783032295316","9783032295323"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-29532-3_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,4]]},"assertion":[{"value":"4 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLDB","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Applications of Natural Language to Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Trondheim","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 June 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nldb2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ntnu.edu\/nldb2026","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}