{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:10:54Z","timestamp":1784178654887,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":69,"publisher":"ACM","funder":[{"name":"European Union ? Next Generation EU"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,13]]},"DOI":"10.1145\/3726302.3730216","type":"proceedings-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T01:38:52Z","timestamp":1752457132000},"page":"2738-2743","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Investigating Task Arithmetic for Zero-Shot Information Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7619-8399","authenticated-orcid":false,"given":"Marco","family":"Braga","sequence":"first","affiliation":[{"name":"Department of Informatics, Systems and Communication - DISCo, University of Milano-Bicocca, Milan, Italy and DAUIN Dipartimento di Automatica e Informatica, Politecnico di Torino, Turin, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0972-2424","authenticated-orcid":false,"given":"Pranav","family":"Kasela","sequence":"additional","affiliation":[{"name":"Department of Informatics, Systems and Communication - DISCo, University of Milano-Bicocca, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7018-7515","authenticated-orcid":false,"given":"Alessandro","family":"Raganato","sequence":"additional","affiliation":[{"name":"Department of Informatics, Systems and Communication - DISCo, University of Milano-Bicocca, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6080-8170","authenticated-orcid":false,"given":"Gabriella","family":"Pasi","sequence":"additional","affiliation":[{"name":"Department of Informatics, Systems and Communication - DISCo, University of Milano-Bicocca, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.130"},{"key":"e_1_3_2_1_2_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Ainsworth Samuel","year":"2023","unstructured":"Samuel Ainsworth, Jonathan Hayase, and Siddhartha Srinivasa. 2023. Git Re-Basin: Merging Models modulo Permutation Symmetries. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","first-page":"1214","volume-title":"Findings of the Association for Computational Linguistics: EACL 2024","author":"Almeida Tiago","year":"2024","unstructured":"Tiago Almeida and S\u00e9rgio Matos. 2024. Exploring efficient zero-shot synthetic dataset generation for Information Retrieval. In Findings of the Association for Computational Linguistics: EACL 2024, Yvette Graham and Matthew Purver (Eds.). Association for Computational Linguistics, St. Julian's, Malta, 1214-1231. https:\/\/aclanthology.org\/2024.findings-eacl.81\/"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.421"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557536"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.762"},{"key":"e_1_3_2_1_7_1","volume-title":"Israel Campiotti, Marzieh Fadaee, Roberto Lotufo, and Rodrigo Nogueira.","author":"Bonifacio Luiz Henrique","year":"2021","unstructured":"Luiz Henrique Bonifacio, Vitor Jeronymo, Hugo Queiroz Abonizio, Israel Campiotti, Marzieh Fadaee, Roberto Lotufo, and Rodrigo Nogueira. 2021. mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset. arxiv: 2108.13897 [cs.CL]"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657917"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_58"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657657"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Marco Braga Pranav Kasela Alessandro Raganato and Gabriella Pasi. 2024a. Synthetic Data Generation with Large Language Models for Personalized Community Question Answering. In 2024 IEEE\/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT).","DOI":"10.1109\/WI-IAT62293.2024.00057"},{"key":"e_1_3_2_1_12_1","first-page":"350","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024","author":"Braga Marco","year":"2024","unstructured":"Marco Braga, Alessandro Raganato, and Gabriella Pasi. 2024b. AdaKron: An Adapter-based Parameter Efficient Model Tuning with Kronecker Product. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 350-357. https:\/\/aclanthology.org\/2024.lrec-main.32\/"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 13th Italian Information Retrieval Workshop (IIR","author":"Braga Marco","year":"2023","unstructured":"Marco Braga, Alessandro Raganato, Gabriella Pasi, et al. 2023. Personalization in BERT with Adapter Modules and Topic Modelling. In Proceedings of the 13th Italian Information Retrieval Workshop (IIR 2023). Pisa, Italy. 24-29."},{"key":"e_1_3_2_1_14_1","first-page":"1877","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877-1901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_15_1","unstructured":"R\u00e9mi Calizzano Malte Ostendorff Qian Ruan and Georg Rehm. 2022. Generating Extended and Multilingual Summaries with Pre-trained Transformers. In Proceedings of the Thirteenth Language Resources and Evaluation Conference Nicoletta Calzolari Fr\u00e9d\u00e9ric B\u00e9chet Philippe Blache Khalid Choukri Christopher Cieri Thierry Declerck Sara Goggi Hitoshi Isahara Bente Maegaard Joseph Mariani H\u00e9l\u00e8ne Mazo Jan Odijk and Stelios Piperidis (Eds.). European Language Resources Association Marseille France 1640-1650. https:\/\/aclanthology.org\/2022.lrec-1.175\/"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.708"},{"key":"e_1_3_2_1_17_1","volume-title":"Fusing finetuned models for better pretraining. arXiv preprint arXiv:2204.03044","author":"Choshen Leshem","year":"2022","unstructured":"Leshem Choshen, Elad Venezian, Noam Slonim, and Yoav Katz. 2022. Fusing finetuned models for better pretraining. arXiv preprint arXiv:2204.03044 (2022)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.mrl-1.7"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.207"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.393"},{"key":"e_1_3_2_1_21_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_22_1","volume-title":"The Early Phase of Neural Network Training. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hkl1iRNFwS","author":"Frankle Jonathan","unstructured":"Jonathan Frankle, David J. Schwab, and Ari S. Morcos. 2020. The Early Phase of Neural Network Training. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Hkl1iRNFwS"},{"key":"e_1_3_2_1_23_1","volume-title":"Smith","author":"Gururangan Suchin","year":"2020","unstructured":"Suchin Gururangan, Ana Marasovic, Swabha Swayamdipta, Kyle Lo, Iz Beltagy, Doug Downey, and Noah A. Smith. 2020. Don't Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of ACL."},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 2790-2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790-2799."},{"key":"e_1_3_2_1_25_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.590"},{"key":"e_1_3_2_1_27_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Ilharco Gabriel","year":"2022","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2022. Editing models with task arithmetic. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","volume-title":"34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018. Association For Uncertainty in Artificial Intelligence (AUAI), 876-885","author":"Izmailov Pavel","year":"2018","unstructured":"Pavel Izmailov, Dmitrii Podoprikhin, Timur Garipov, Dmitry Vetrov, and Andrew Gordon Wilson. 2018. Averaging weights leads to wider optima and better generalization. In 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018. Association For Uncertainty in Artificial Intelligence (AUAI), 876-885."},{"key":"e_1_3_2_1_29_1","volume-title":"Introduction to transformers for NLP: With the hugging face library and models to solve problems","author":"Jain Shashank Mohan","unstructured":"Shashank Mohan Jain. 2022. Hugging face. In Introduction to transformers for NLP: With the hugging face library and models to solve problems. Springer, 51-67."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657862"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3651445"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56060-6_8"},{"key":"e_1_3_2_1_33_1","volume-title":"Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models. In First Workshop on Interpolation Regularizers and Beyond at NeurIPS","author":"Li Margaret","year":"2022","unstructured":"Margaret Li, Suchin Gururangan, Tim Dettmers, Mike Lewis, Tim Althoff, Noah A. Smith, and Luke Zettlemoyer. 2022. Branch-Train-Merge: Embarrassingly Parallel Training of Expert Language Models. In First Workshop on Interpolation Regularizers and Beyond at NeurIPS 2022. https:\/\/openreview.net\/forum?id=SQgVgE2Sq4"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657979"},{"key":"e_1_3_2_1_35_1","volume-title":"Pretrained transformers for text ranking: Bert and beyond","author":"Lin Jimmy","unstructured":"Jimmy Lin, Rodrigo Nogueira, and Andrew Yates. 2022. Pretrained transformers for text ranking: Bert and beyond. Springer Nature."},{"key":"e_1_3_2_1_36_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv","author":"Liu Yinhan","year":"1907","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arxiv: 1907.11692 [cs.CL] https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.433"},{"key":"e_1_3_2_1_38_1","first-page":"17703","article-title":"Merging models with fisher-weighted averaging","volume":"35","author":"Matena Michael S","year":"2022","unstructured":"Michael S Matena and Colin A Raffel. 2022. Merging models with fisher-weighted averaging. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17703-17716.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.mrqa-1.4"},{"key":"e_1_3_2_1_41_1","unstructured":"Tri Nguyen Mir Rosenberg Xia Song Jianfeng Gao Saurabh Tiwary Rangan Majumder and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In Proceedings of the Workshop on Cognitive Computation: Integrating neural and symbolic approaches 2016 co-located with the 30th Annual Conference on Neural Information Processing Systems (NIPS 2016) Barcelona Spain December 9 2016 (CEUR Workshop Proceedings Vol. 1773) Tarek Richard Besold Antoine Bordes Artur S. d'Avila Garcez and Greg Wayne (Eds.). CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-1773\/CoCoNIPS_2016_paper9.pdf"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.63"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-short.12"},{"key":"e_1_3_2_1_44_1","volume-title":"Scifive: a text-to-text transformer model for biomedical literature. arXiv preprint arXiv:2106.03598","author":"Phan Long N","year":"2021","unstructured":"Long N Phan, James T Anibal, Hieu Tran, Shaurya Chanana, Erol Bahadroglu, Alec Peltekian, and Gr\u00e9goire Altan-Bonnet. 2021. Scifive: a text-to-text transformer model for biomedical literature. arXiv preprint arXiv:2106.03598 (2021)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.97"},{"key":"e_1_3_2_1_46_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_3_2_1_48_1","volume-title":"Proceedings of the 14th Italian Information Retrieval Workshop, Udine, Italy, September 5-6, 2024 (CEUR Workshop Proceedings","volume":"32","author":"Rizzo Daniele","year":"2024","unstructured":"Daniele Rizzo, Alessandro Raganato, and Marco Viviani. 2024. Comparatively Assessing Large Language Models for Query Expansion in Information Retrieval via Zero-Shot and Chain-of-Thought Prompting. In Proceedings of the 14th Italian Information Retrieval Workshop, Udine, Italy, September 5-6, 2024 (CEUR Workshop Proceedings, Vol. 3802). CEUR-WS.org, 23-32. https:\/\/ceur-ws.org\/Vol-3802\/paper22.pdf"},{"key":"e_1_3_2_1_49_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Rogers Anna","year":"2024","unstructured":"Anna Rogers and Sasha Luccioni. 2024. Position: Key Claims in LLM Research Have a Long Tail of Footnotes. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_50_1","volume-title":"Bioinformatics","volume":"39","author":"Rohanian Omid","year":"2023","unstructured":"Omid Rohanian, Mohammadmahdi Nouriborji, Samaneh Kouchaki, and David A Clifton. 2023. On the effectiveness of compact biomedical transformers. Bioinformatics, Vol. 39, 3 (2023), btad103."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.103007"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of Thirty-third Conference on Neural Information Processing Systems (NIPS2019)","author":"Sanh V","year":"2019","unstructured":"V Sanh. 2019. DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. In Proceedings of Thirty-third Conference on Neural Information Processing Systems (NIPS2019)."},{"key":"e_1_3_2_1_53_1","volume-title":"Baptiste Rozi\u00e8re, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, et al.","author":"Sukhbaatar Sainbayar","year":"2024","unstructured":"Sainbayar Sukhbaatar, Olga Golovneva, Vasu Sharma, Hu Xu, Xi Victoria Lin, Baptiste Rozi\u00e8re, Jacob Kahn, Daniel Li, Wen-tau Yih, Jason Weston, et al. 2024. Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM. arXiv preprint arXiv:2403.07816 (2024)."},{"key":"e_1_3_2_1_54_1","volume-title":"BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2).","author":"Thakur Nandan","year":"2021","unstructured":"Nandan Thakur, Nils Reimers, Andreas R\u00fcckl\u00e9, Abhishek Srivastava, and Iryna Gurevych. 2021. BEIR: A Heterogeneous Benchmark for Zero-shot Evaluation of Information Retrieval Models. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)."},{"key":"e_1_3_2_1_55_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi and Yasmine Babaei et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arxiv: 2307.09288 [cs.CL] https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3451964.3451965"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.609"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3178128"},{"key":"e_1_3_2_1_59_1","volume-title":"Zero-shot Generative Large Language Models for Systematic Review Screening Automation. In European Conference on Information Retrieval. Springer, 403-420","author":"Wang Shuai","year":"2024","unstructured":"Shuai Wang, Harrisen Scells, Shengyao Zhuang, Martin Potthast, Bevan Koopman, and Guido Zuccon. 2024. Zero-shot Generative Large Language Models for Systematic Review Screening Automation. In European Conference on Information Retrieval. Springer, 403-420."},{"key":"e_1_3_2_1_60_1","volume-title":"International conference on machine learning. PMLR, 23965-23998","author":"Wortsman Mitchell","year":"2022","unstructured":"Mitchell Wortsman, Gabriel Ilharco, Samir Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, et al. 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In International conference on machine learning. PMLR, 23965-23998."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC63097.2024.00027"},{"key":"e_1_3_2_1_62_1","volume-title":"mT5: A massively multilingual pre-trained text-to-text transformer. arxiv","author":"Xue Linting","year":"2010","unstructured":"Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual pre-trained text-to-text transformer. arxiv: 2010.11934 [cs.CL] https:\/\/arxiv.org\/abs\/2010.11934"},{"key":"e_1_3_2_1_63_1","first-page":"7093","article-title":"Ties-merging: Resolving interference when merging models","volume":"36","author":"Yadav Prateek","year":"2023","unstructured":"Prateek Yadav, Derek Tam, Leshem Choshen, Colin A Raffel, and Mohit Bansal. 2023. Ties-merging: Resolving interference when merging models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 7093-7115.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_64_1","volume-title":"Forty-first International Conference on Machine Learning.","author":"Yu Le","year":"2024","unstructured":"Le Yu, Bowen Yu, Haiyang Yu, Fei Huang, and Yongbin Li. 2024. Language models are super mario: Absorbing abilities from homologous models as a free lunch. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_1_65_1","volume-title":"Disentangled modeling of domain and relevance for adaptable dense retrieval. arXiv preprint arXiv:2208.05753","author":"Zhan Jingtao","year":"2022","unstructured":"Jingtao Zhan, Qingyao Ai, Yiqun Liu, Jiaxin Mao, Xiaohui Xie, Min Zhang, and Shaoping Ma. 2022. Disentangled modeling of domain and relevance for adaptable dense retrieval. arXiv preprint arXiv:2208.05753 (2022)."},{"key":"e_1_3_2_1_66_1","unstructured":"Longhui Zhang Yanzhao Zhang Dingkun Long Pengjun Xie Meishan Zhang and Min Zhang. 2023b. RankingGPT: Empowering Large Language Models in Text Ranking with Progressive Enhancement. arxiv: 2311.16720 [cs.IR]"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00595"},{"key":"e_1_3_2_1_68_1","volume-title":"Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107","author":"Zhu Yutao","year":"2023","unstructured":"Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Haonan Chen, Zheng Liu, Zhicheng Dou, and Ji-Rong Wen. 2023. Large language models for information retrieval: A survey. arXiv preprint arXiv:2308.07107 (2023)."},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657813"}],"event":{"name":"SIGIR '25: The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Padua Italy","acronym":"SIGIR '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"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\/3726302.3730216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:09:26Z","timestamp":1755864566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3726302.3730216"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,13]]},"references-count":69,"alternative-id":["10.1145\/3726302.3730216","10.1145\/3726302"],"URL":"https:\/\/doi.org\/10.1145\/3726302.3730216","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"}}]}}