{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:46:06Z","timestamp":1777016766671,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3799830.3799852","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:45:08Z","timestamp":1777013108000},"page":"199-207","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adapting Multilingual Models to Code-Mixed Tasks via Model Merging"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7542-6802","authenticated-orcid":false,"given":"Prashant","family":"Kodali","sequence":"first","affiliation":[{"name":"IIIT Hyderabad, Hyderabad, Telangana, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1870-6859","authenticated-orcid":false,"given":"Vaishnavi","family":"Shivkumar","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad, Hyderabad, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3609-4523","authenticated-orcid":false,"given":"Swarang","family":"Joshi","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad, Hyderabad, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7473-7839","authenticated-orcid":false,"given":"Monojit","family":"Choudhury","sequence":"additional","affiliation":[{"name":"MBZUAI, Abu Dhabi, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5082-2078","authenticated-orcid":false,"given":"Ponnurangam","family":"Kumaraguru","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad, Hyderabad, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8705-6637","authenticated-orcid":false,"given":"Manish","family":"Shrivastava","sequence":"additional","affiliation":[{"name":"IIIT Hyderabad, Hyderabad, India"}]}],"member":"320","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"1803","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"Aguilar Gustavo","year":"2020","unstructured":"Gustavo Aguilar, Sudipta Kar, and Thamar Solorio. 2020. LinCE: A Centralized Benchmark for Linguistic Code-switching Evaluation. In Proceedings of the Twelfth 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, Asuncion Moreno, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association, Marseille, France, 1803\u20131813. https:\/\/aclanthology.org\/2020.lrec-1.223"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.716"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.1000"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1105"},{"key":"e_1_3_3_2_6_2","first-page":"177","volume-title":"Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)","author":"Chakravarthi Bharathi\u00a0Raja","year":"2020","unstructured":"Bharathi\u00a0Raja Chakravarthi, Navya Jose, Shardul Suryawanshi, Elizabeth Sherly, and John\u00a0Philip McCrae. 2020. A Sentiment Analysis Dataset for Code-Mixed Malayalam-English. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), Dorothee Beermann, Laurent Besacier, Sakriani Sakti, and Claudia Soria (Eds.). European Language Resources association, Marseille, France, 177\u2013184. https:\/\/aclanthology.org\/2020.sltu-1.25"},{"key":"e_1_3_3_2_7_2","first-page":"202","volume-title":"Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)","author":"Chakravarthi Bharathi\u00a0Raja","year":"2020","unstructured":"Bharathi\u00a0Raja Chakravarthi, Vigneshwaran Muralidaran, Ruba Priyadharshini, and John\u00a0Philip McCrae. 2020. Corpus Creation for Sentiment Analysis in Code-Mixed Tamil-English Text. In Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL), Dorothee Beermann, Laurent Besacier, Sakriani Sakti, and Claudia Soria (Eds.). European Language Resources association, Marseille, France, 202\u2013210. https:\/\/aclanthology.org\/2020.sltu-1.28"},{"key":"e_1_3_3_2_8_2","unstructured":"Leshem Choshen Elad Venezian Noam Slonim and Yoav Katz. 2022. Fusing finetuned models for better pretraining. arXiv:https:\/\/arXiv.org\/abs\/2204.03044\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2204.03044"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.66"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.131"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Charles Goddard Shamane Siriwardhana Malikeh Ehghaghi Luke Meyers Vlad Karpukhin Brian Benedict Mark McQuade and Jacob Solawetz. 2024. Arcee\u2019s MergeKit: A Toolkit for Merging Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.13257 (2024).","DOI":"10.18653\/v1\/2024.emnlp-industry.36"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70563-2_6"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"John\u00a0J Gumperz. 1977. The sociolinguistic significance of conversational code-switching. RELC journal 8 2 (1977) 1\u201334.","DOI":"10.1177\/003368827700800201"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"e_1_3_3_2_17_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ilharco Gabriel","year":"2023","unstructured":"Gabriel Ilharco, Marco\u00a0Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2023. Editing models with task arithmetic. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6t0Kwf8-jrj"},{"key":"e_1_3_3_2_18_2","volume-title":"Conference on Uncertainty in Artificial Intelligence","author":"Izmailov Pavel","year":"2018","unstructured":"Pavel Izmailov, Dmitrii Podoprikhin, T. Garipov, Dmitry\u00a0P. Vetrov, and Andrew\u00a0Gordon Wilson. 2018. Averaging Weights Leads to Wider Optima and Better Generalization. In Conference on Uncertainty in Artificial Intelligence. https:\/\/api.semanticscholar.org\/CorpusID:3833416"},{"key":"e_1_3_3_2_19_2","volume-title":"The Eleventh International Conference on Learning Representations","author":"Jin Xisen","year":"2023","unstructured":"Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, and Pengxiang Cheng. 2023. Dataless Knowledge Fusion by Merging Weights of Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=FCnohuR6AnM"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Simran Khanuja Sandipan Dandapat Anirudh Srinivasan Sunayana Sitaram and Monojit Choudhury. 2020. GLUECoS: An evaluation benchmark for code-switched NLP. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.12376 (2020).","DOI":"10.18653\/v1\/2020.acl-main.329"},{"key":"e_1_3_3_2_21_2","unstructured":"Prashant Kodali Anmol Goel Likhith Asapu Vamshi\u00a0Krishna Bonagiri Anirudh Govil Monojit Choudhury Manish Shrivastava and Ponnurangam Kumaraguru. 2024. From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences. arXiv:https:\/\/arXiv.org\/abs\/2405.05572\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2405.05572"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.239"},{"key":"e_1_3_3_2_23_2","unstructured":"Sourab Mangrulkar Sylvain Gugger Lysandre Debut Younes Belkada Sayak Paul and Benjamin Bossan. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_3_2_24_2","unstructured":"Benjamin Muller Benoit Sagot and Djam\u00e9 Seddah. 2020. Can Multilingual Language Models Transfer to an Unseen Dialect? A Case Study on North African Arabizi. arXiv:https:\/\/arXiv.org\/abs\/2005.00318\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2005.00318"},{"key":"e_1_3_3_2_25_2","first-page":"37","volume-title":"Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop","author":"Pant Kartikey","year":"2020","unstructured":"Kartikey Pant and Tanvi Dadu. 2020. Towards Code-switched Classification Exploiting Constituent Language Resources. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing: Student Research Workshop, Boaz Shmueli and Yin\u00a0Jou Huang (Eds.). Association for Computational Linguistics, Suzhou, China, 37\u201343. https:\/\/aclanthology.org\/2020.aacl-srw.6"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.semeval-1.100"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1493"},{"key":"e_1_3_3_2_28_2","volume-title":"International Conference on Computational Linguistics","author":"Prabhu Ameya","year":"2016","unstructured":"Ameya Prabhu, Aditya Joshi, Manish Shrivastava, and Vasudeva Varma. 2016. Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text. In International Conference on Computational Linguistics. https:\/\/api.semanticscholar.org\/CorpusID:5068554"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503162.3503177"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.63317\/5ody4yffoe3q"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-demos.24"},{"key":"e_1_3_3_2_32_2","unstructured":"Sebastian Ruder. 2021. Recent Advances in Language Model Fine-tuning. http:\/\/ruder.io\/recent-advances-lm-fine-tuning."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"e_1_3_3_2_34_2","first-page":"19","volume-title":"Proceedings of the 15th International Conference on Natural Language Generation: Generation Challenges","author":"Srivastava Vivek","year":"2022","unstructured":"Vivek Srivastava and Mayank Singh. 2022. HinglishEval Generation Challenge on Quality Estimation of Synthetic Code-Mixed Text: Overview and Results. In Proceedings of the 15th International Conference on Natural Language Generation: Generation Challenges, Samira Shaikh, Thiago Ferreira, and Amanda Stent (Eds.). Association for Computational Linguistics, Waterville, Maine, USA and virtual meeting, 19\u201325. https:\/\/aclanthology.org\/2022.inlg-genchal.3"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.282"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.185"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.calcs-1.20"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_3_2_39_2","series-title":"Proceedings of Machine Learning Research","first-page":"23965","volume-title":"Proceedings of the 39th International Conference on Machine Learning","volume":"162","author":"Wortsman Mitchell","year":"2022","unstructured":"Mitchell Wortsman, Gabriel Ilharco, Samir\u00a0Ya Gadre, Rebecca Roelofs, Raphael Gontijo-Lopes, Ari\u00a0S Morcos, Hongseok Namkoong, Ali Farhadi, Yair Carmon, Simon Kornblith, and Ludwig Schmidt. 2022. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In Proceedings of the 39th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0162), Kamalika Chaudhuri, Stefanie Jegelka, Le\u00a0Song, Csaba Szepesvari, Gang Niu, and Sivan Sabato (Eds.). PMLR, 23965\u201323998. https:\/\/proceedings.mlr.press\/v162\/wortsman22a.html"},{"key":"e_1_3_3_2_40_2","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems","author":"Yadav Prateek","year":"2023","unstructured":"Prateek Yadav, Derek Tam, Leshem Choshen, Colin Raffel, and Mohit Bansal. 2023. TIES-Merging: Resolving Interference When Merging Models. In Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=xtaX3WyCj1"},{"key":"e_1_3_3_2_41_2","unstructured":"Enneng Yang Li Shen Guibing Guo Xingwei Wang Xiaochun Cao Jie Zhang and Dacheng Tao. 2024. Model Merging in LLMs MLLMs and Beyond: Methods Theories Applications and Opportunities. arXiv:https:\/\/arXiv.org\/abs\/2408.07666\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2408.07666"},{"key":"e_1_3_3_2_42_2","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. arXiv:https:\/\/arXiv.org\/abs\/2311.03099\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2311.03099"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Ruochen Zhang Samuel Cahyawijaya Jan Christian\u00a0Blaise Cruz Genta\u00a0Indra Winata and Alham\u00a0Fikri Aji. 2023. Multilingual large languageLince: A centralized benchmark for linguis- tic code-switching evaluation models are not (yet) code-switchers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.14235 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.774"}],"event":{"name":"CODS 2025: 13th ACM IKDD International Conference on Data Science","location":"Pune India","acronym":"CODS 2025"},"container-title":["Proceedings of the 13th ACM IKDD International Conference on Data Science"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799830.3799852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:16:26Z","timestamp":1777014986000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799830.3799852"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":42,"alternative-id":["10.1145\/3799830.3799852","10.1145\/3799830"],"URL":"https:\/\/doi.org\/10.1145\/3799830.3799852","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}