{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T08:10:07Z","timestamp":1751703007601,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031976346","type":"print"},{"value":"9783031976353","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-97635-3_19","type":"book-chapter","created":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T07:41:56Z","timestamp":1751701316000},"page":"154-162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Is Heterogeneous Model Soup Tasty? A Multidimensional Evaluation of\u00a0Diverse Model Soups in\u00a0Language Model Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6222-8557","authenticated-orcid":false,"given":"Dawid","family":"Motyka","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0381-9202","authenticated-orcid":false,"given":"Pawe\u0142","family":"Walkowiak","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8581-1098","authenticated-orcid":false,"given":"Julia","family":"Moska","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8473-7718","authenticated-orcid":false,"given":"Bartosz","family":"\u017buk","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-7301","authenticated-orcid":false,"given":"Karolina","family":"Seweryn","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9203-5520","authenticated-orcid":false,"given":"Arkadiusz","family":"Janz","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,6]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal, S., Mandowara, D., Agrawal, V., Khandelwal, D., Singla, P., Garg, D.: Explanations for CommonsenseQA: new dataset and models. In: ACL. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.238"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Croce, F., Rebuffi, S.A., Shelhamer, E., Gowal, S.: Seasoning model soups for robustness to adversarial and natural distribution shifts (2023)","DOI":"10.1109\/CVPR52729.2023.01185"},{"key":"19_CR3","unstructured":"Ethayarajh, K., Xu, W., Muennighoff, N., Jurafsky, D., Kiela, D.: KTO: model alignment as prospect theoretic optimization (2024)"},{"key":"19_CR4","unstructured":"Frankle, J., Dziugaite, G.K., Roy, D.M., Carbin, M.: Linear mode connectivity and the lottery ticket hypothesis (2019)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Hong, J., Lee, N., Thorne, J.: Orpo: monolithic preference optimization without reference model (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.626"},{"key":"19_CR6","unstructured":"Ilharco, G., Ribeiro, M.T., Wortsman, M., Gururangan, S., Schmidt, L., Hajishirzi, H., et\u00a0al.: Editing models with task arithmetic (2022)"},{"key":"19_CR7","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization (2018)"},{"key":"19_CR8","unstructured":"Jang, J., et\u00a0al.: Personalized soups: personalized large language model alignment via post-hoc parameter merging (2023)"},{"key":"19_CR9","unstructured":"Jang, J., Kim, S., Ye, S., Kim, D., Logeswaran, L., Lee, M., et\u00a0al.: Exploring the benefits of training expert language models over instruction tuning (2023)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Lamm, M., Palomaki, J., Alberti, C., Andor, D., Choi, E., Soares, L.B., et\u00a0al.: Qed: a framework and dataset for explanations in question answering (2020)","DOI":"10.1162\/tacl_a_00398"},{"key":"19_CR11","unstructured":"Li, X., et al.: Alpacaeval: an automatic evaluator of instruction-following models (2023)"},{"key":"19_CR12","unstructured":"Mirzadeh, S.I., Farajtabar, M., Gorur, D., Pascanu, R., Ghasemzadeh, H.: Linear mode connectivity in multitask and continual learning (2020)"},{"key":"19_CR13","unstructured":"Neyshabur, B., Sedghi, H., Zhang, C.: What is being transferred in transfer learning? In: NeurIPS 2020 (2020)"},{"key":"19_CR14","unstructured":"Onoe, Y., Zhang, M.J., Choi, E., Durrett, G.: Creak: a dataset for commonsense reasoning over entity knowledge. OpenReview (2021)"},{"key":"19_CR15","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D., Finn, C.: Direct preference optimization: your language model is secretly a reward model (2023)"},{"key":"19_CR16","unstructured":"Rame, A., Couairon, G., Dancette, C., Gaya, J.B., Shukor, M., Soulier, L., et\u00a0al.: Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. In: NeurIPS (2023)"},{"key":"19_CR17","unstructured":"Ram\u00e9, A., Ahuja, K., Zhang, J., Cord, M., Bottou, L., Lopez-Paz, D.: Model ratatouille: recycling diverse models for out-of-distribution generalization (2022)"},{"key":"19_CR18","unstructured":"Ram\u00e9, A., Ferret, J., Vieillard, N., Dadashi, R., Hussenot, L., Cedoz, P.L., et\u00a0al.: Warp: on the benefits of weight averaged rewarded policies (2024)"},{"key":"19_CR19","unstructured":"Ram\u00e9, A., Kirchmeyer, M., Rahier, T., Rakotomamonjy, A., Gallinari, P., Cord, M.: Diverse weight averaging for out-of-distribution generalization (2022)"},{"key":"19_CR20","unstructured":"Wortsman, M., Ilharco, G., Gadre, S.Y., Roelofs, R., Gontijo-Lopes, R., Morcos, A.S., et\u00a0al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time (2022)"},{"key":"19_CR21","unstructured":"Zheng, L., Chiang, W., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., et\u00a0al.: Judging llm-as-a-judge with mt-bench and chatbot arena. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) NeurIPS (2023)"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97635-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T07:42:03Z","timestamp":1751701323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97635-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031976346","9783031976353"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97635-3_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"6 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}