{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T03:44:38Z","timestamp":1777434278620,"version":"3.51.4"},"reference-count":81,"publisher":"SAGE Publications","issue":"1","license":[{"start":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T00:00:00Z","timestamp":1769558400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100006687","name":"Universit\u00e9 Claude Bernard Lyon 1","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006687","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Argument &amp; Computation"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>Argument mining is a subfield of argumentation that aims to automatically extract argumentative structures and their relations from natural language texts. This article investigates how a single large language model can be leveraged to perform one or several argument mining tasks. Our contributions are two-fold. First, we construct a multi-task dataset by surveying and converting 19 well-known argument mining datasets from the literature into a unified format. Second, we explore various training strategies using Meta AI\u2019s Llama-3.1-8B-Instruct model: (1) fine-tuning on individual tasks, (2) fine-tuning jointly on multiple tasks, and (3) merging models fine-tuned separately on individual tasks. Our experiments show that task-specific fine-tuning significantly improves individual performance across all tasks. Moreover, multi-task fine-tuning maintains strong performance without degradation, suggesting effective transfer learning across related tasks. Finally, we demonstrate that model merging offers a viable compromise: it yields competitive performance while mitigating the computational costs associated with full multi-task fine-tuning.<\/jats:p>","DOI":"10.1177\/19462174251413169","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T17:31:23Z","timestamp":1769621483000},"page":"79-103","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["AMELIA: A family of multi-task end-to-end language models for\u00a0argumentation"],"prefix":"10.1177","volume":"17","author":[{"given":"Henri","family":"Savigny","sequence":"first","affiliation":[{"name":"Universite Claude Bernard Lyon 1, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9370-3917","authenticated-orcid":false,"given":"Bruno","family":"Yun","sequence":"additional","affiliation":[{"name":"Universite Claude Bernard Lyon 1, France"},{"name":"CNRS, Ecole Centrale de Lyon, INSA Lyon, Universit\u00e9 Lumi\u00e8re Lyon 2, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(94)00041-X"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","unstructured":"Croitoru M Vesic S. What can argumentation do for inconsistent ontology query answering? In: Liu W Subrahmanian VS and Wijsen J (eds) Scalable uncertainty management \u2013 7th international conference SUM 2013 Washington DC USA 16\u201318 September 2013. Proceedings Volume 8078 Lecture notes in computer science 2013 pp.15\u201329. Berlin Heidelberg: Springer.\u00a010.1007\/978-3-642-40381-1_2","DOI":"10.1007\/978-3-642-40381-1_2"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.3233\/AAC-210007"},{"key":"e_1_3_3_5_2","unstructured":"Amgoud L Cayrol C Lagasquie-Schiex M. On the bipolarity in argumentation frameworks. In: Delgrande JP and Schaub T (eds) 10th international workshop on non-monotonic reasoning (NMR 2004) Whistler Canada 6\u20138 June 2004 proceedings 2004 pp.1\u20139. http:\/\/www.pims.math.ca\/science\/2004\/NMR\/papers\/paper01.pdf."},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Yun B Vesic S. Gradual semantics for weighted bipolar setafs. In: Vejnarov\u00e1 J and Wilson N (eds) Symbolic and quantitative approaches to reasoning with uncertainty \u2013 16th European conference ECSQARU 2021 Prague Czech Republic 21\u201324 September 2021 proceedings Volume 12897 Lecture notes in computer science 2021 pp.201\u2013214. Cham Switzerland: Springer. 10.1007\/978-3-030-86772-0_15","DOI":"10.1007\/978-3-030-86772-0_15"},{"key":"e_1_3_3_7_2","unstructured":"Nielsen SH Parsons S. Computing preferred extensions for argumentation systems with sets of attacking arguments. In: Dunne PE and Bench-Capon TJM (eds) Computational models of argument: proceedings of COMMA 2006 11\u201312 September 2006 Liverpool UK Volume 144 Frontiers in artificial intelligence and applications 2006 pp.97\u2013108. Amsterdam The Netherlands: IOS Press. http:\/\/www.booksonline.iospress.nl\/Content\/View.aspx?piid=1930."},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","unstructured":"Yun B Vesic S Croitoru M. Sets of attacking arguments for inconsistent datalog knowledge bases. In: Prakken H Bistarelli S Santini F and Taticchi C (eds) Computational models of argument \u2013 proceedings of COMMA 2020 Perugia Italy 4\u201311 September 2020 Volume 326 Frontiers in artificial intelligence and applications 2020 pp.419\u2013430. Amsterdam The Netherlands: IOS Press. 10.3233\/FAIA200526","DOI":"10.3233\/FAIA200526"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103607"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","unstructured":"Yun B Vesic S Croitoru M. Ranking-based semantics for sets of attacking arguments. In: The thirty-fourth AAAI conference on artificial intelligence AAAI 2020 the thirty-second innovative applications of artificial intelligence conference IAAI 2020 the tenth AAAI symposium on educational advances in artificial intelligence EAAI 2020 New York NY USA 7\u201312 February 2020 2020 pp.3033\u20133040. Palo Alto California USA: AAAI Press. 10.1609\/aaai.v34i03.5697","DOI":"10.1609\/aaai.v34i03.5697"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2008.11.006"},{"key":"e_1_3_3_12_2","unstructured":"Cramer M Guillaume M. Directionality of attacks in natural language argumentation. In: Schon C (ed) Proceedings of the fourth workshop on bridging the gap between human and automated reasoningco-located with the 27th international joint conference on artificial intelligence and the 23rd European conference on artificial intelligence (IJCAI-ECAI 2018) Stockholm Schweden 14 July 201 Volume 2261 CEUR workshop proceedings 2018 pp.40\u201346. Aachen Germany: CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-2261\/paper7.pdf."},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00364"},{"key":"e_1_3_3_14_2","unstructured":"Figueras BC. Using argumentation theory to fight misinformation. In: Bonet-Jover A Calvo DV Pastor EL Molina-Gonz\u00e1lez MD and Jim\u00e9nez-Zafra SM (eds) Proceedings of the doctoral symposium on natural language processing (NLP-DS 2024) held as part of the XL edition of the international conference of the Spanish society for natural language processing (SEPLN 2024) Valladolid Spain 26 September 2024 Volume 3797 CEUR workshop proceedings 2024 pp.114\u2013122. Aachen Germany: CEUR-WS.org. https:\/\/ceur-ws.org\/Vol-3797\/paper14.pdf."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1177\/19462174251330980"},{"key":"e_1_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Niculae V Park J Cardie C. Argument mining with structured SVMS and RNNS 2017. arXiv preprint arXiv:1704.06869.","DOI":"10.18653\/v1\/P17-1091"},{"key":"e_1_3_3_17_2","unstructured":"Mayer T Cabrio E Villata S. Transformer-based argument mining for healthcare applications. In: ECAI 2020 2020 pp.2108\u20132115.\u00a0Amsterdam The Netherlands: IOS Press."},{"key":"e_1_3_3_18_2","unstructured":"Cabessa J Hernault H Mushtaq U. Argument mining with fine-tuned large language models. In: Proceedings of the 31st international conference on computational linguistics 2025 pp.6624\u20136635. Abu Dhabi United Arab Emirates: Association for Computational Linguistics."},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Faugier E Armetta F Bonifati A et al. Assisted debate builder with large language models. In: ECAI 2024 2024 pp.4447\u20134450.\u00a0Amsterdam The Netherlands: IOS Press.","DOI":"10.3233\/FAIA241026"},{"key":"e_1_3_3_20_2","unstructured":"Gorur D Rago A Toni F. Can large language models perform relation-based argument mining? In: Rambow O Wanner L Apidianaki M Al-Khalifa H Eugenio BD and Schockaert S (eds) Proceedings of the 31st international conference on computational linguistics COLING 2025 Abu Dhabi UAE 19\u201324 January 2025 2025 pp.8518\u20138534. Abu Dhabi United Arab Emirates: Association for Computational Linguistics. https:\/\/aclanthology.org\/2025.coling-main.569\/."},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Stahl M Ziegenbein T Park J et al. Arginstruct: specialized instruction fine-tuning for computational argumentation 2025. arXiv preprint arXiv:2505.22076.","DOI":"10.18653\/v1\/2025.findings-acl.579"},{"key":"e_1_3_3_22_2","unstructured":"Mikolov T Chen K Corrado G et al. Efficient estimation of word representations in vector space 2013. arXiv preprint arXiv:1301.3781."},{"issue":"8","key":"e_1_3_3_23_2","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford A","year":"2019","unstructured":"Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners. OpenAI blog 2019; 1(8): 9.","journal-title":"OpenAI blog"},{"key":"e_1_3_3_24_2","unstructured":"Mann B Ryder N Subbiah M et al. Language models are few-shot learners 2020. arXiv preprint arXiv:2005.14165 1: 3."},{"key":"e_1_3_3_25_2","unstructured":"Llama Team. The llama 3 herd of models. CoRR 2024. abs\/2407.21783. https:\/\/doi.org\/10.48550\/arXiv.2407.21783"},{"key":"e_1_3_3_26_2","unstructured":"Jiang AQ Sablayrolles A Mensch A et al. Mistral 7b 2023. https:\/\/arxiv.org\/abs\/2310.06825."},{"key":"e_1_3_3_27_2","unstructured":"Yang A Li A Yang B et al. Qwen3 technical report 2025. arXiv preprint arXiv:2505.09388."},{"key":"e_1_3_3_28_2","unstructured":"Achiam J Adler S Agarwal S et al. Gpt-4 technical report 2023. arXiv preprint arXiv:2303.08774 ."},{"key":"e_1_3_3_29_2","unstructured":"Anthropic. Claude\u2019s extended thinking 2025. https:\/\/www.anthropic.com\/research\/visible-extended-thinking."},{"key":"e_1_3_3_30_2","unstructured":"DeepCogito. Introducing cogito preview 2025. https:\/\/deep-cogito-website.vercel.app\/research\/cogito-v1-preview."},{"key":"e_1_3_3_31_2","unstructured":"Guo D Yang D Zhang H et al. Deepseek-r1: incentivizing reasoning capability in LLMs via reinforcement learning 2025. arXiv preprint arXiv:2501.12948."},{"key":"e_1_3_3_32_2","unstructured":"Liu A Feng B Xue B et al. DeepSeek-V3 technical report 2024. arXiv preprint arXiv:2412.19437."},{"key":"e_1_3_3_33_2","unstructured":"Yang C Wang X et al. QwQ: a high-performance reasoning model for theorem proving and code generation 2024. arXiv preprint arXiv:2404.07158."},{"key":"e_1_3_3_34_2","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei J","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst 2022; 35: 24824\u201324837.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Yao Y Li Z Zhao H. Beyond chain-of-thought effective graph-of-thought reasoning in language models 2023. arXiv preprint arXiv:2305.16582.","DOI":"10.18653\/v1\/2024.findings-naacl.183"},{"key":"e_1_3_3_36_2","unstructured":"Zhou Y Geng X Shen T et al. Thread of thought unraveling chaotic contexts 2023. arXiv preprint arXiv:2311.08734."},{"issue":"70","key":"e_1_3_3_37_2","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung HW","year":"2024","unstructured":"Chung HW, Hou L, Longpre S, et al. Scaling instruction-finetuned language models. J Mach Learn Res 2024; 25(70): 1\u201353.","journal-title":"J Mach Learn Res"},{"issue":"2","key":"e_1_3_3_38_2","first-page":"3","article-title":"Lora: low-rank adaptation of large language models","volume":"1","author":"Hu EJ","year":"2022","unstructured":"Hu EJ, Shen Y, Wallis P, et al. Lora: low-rank adaptation of large language models. ICLR 2022; 1(2): 3.","journal-title":"ICLR"},{"key":"e_1_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Skitalinskaya G Klaff J Wachsmuth H. Learning from revisions: quality assessment of claims in argumentation at scale 2021. arXiv preprint arXiv:2101.10250.","DOI":"10.18653\/v1\/2021.eacl-main.147"},{"key":"e_1_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Wang Y Chen X He B et al. Contextual interaction for argument post quality assessment. In: Proceedings of the 2023 conference on empirical methods in natural language processing 2023 pp.10420\u201310432. Singapore: Association for Computational Linguistics (ACL).","DOI":"10.18653\/v1\/2023.emnlp-main.645"},{"key":"e_1_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Wachsmuth H Naderi N Hou Y et al. Computational argumentation quality assessment in natural language. In: Proceedings of the 15th conference of the European chapter of the association for computational linguistics: volume 1 long papers 2017 pp.176\u2013187. Valencia Spain: Association for Computational Linguistics.","DOI":"10.18653\/v1\/E17-1017"},{"key":"e_1_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Carstens L Toni F. Towards relation based argumentation mining. In: Proceedings of the 2nd workshop on argumentation mining 2015 pp.29\u201334. Denver Colorado USA: The Association for Computational Linguistics.","DOI":"10.3115\/v1\/W15-0504"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00394"},{"key":"e_1_3_3_44_2","doi-asserted-by":"crossref","unstructured":"Menini S Cabrio E Tonelli S et al. Never retreat never retract: argumentation analysis for political speeches. In: McIlraith SA and Weinberger KQ (eds) 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 2018 pp.4889\u20134896. Palo Alto California USA: AAAI Press. https:\/\/doi.org\/10.1609\/aaai.v32i1.11920","DOI":"10.1609\/aaai.v32i1.11920"},{"key":"e_1_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Goffredo P Chaves M Villata S et al. Argument-based detection and classification of fallacies in political debates. In: EMNLP 2023-conference on empirical methods in natural language processing Volume 2023 2023 pp.11101\u201311112. Association for Computational Linguistics\u00a0Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.684"},{"key":"e_1_3_3_46_2","unstructured":"Helwe C Calamai T Paris PH et al. Mafalda: a benchmark and comprehensive study of fallacy detection and classification 2023. arXiv preprint arXiv:2311.09761."},{"key":"e_1_3_3_47_2","unstructured":"Lenz M Sahitaj P Kallenberg S et al. Towards an argument mining pipeline transforming texts to argument graphs. In: Computational models of argument 2020 pp.263\u2013270. Amsterdam The Netherlands: IOS Press."},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00481"},{"key":"e_1_3_3_49_2","doi-asserted-by":"crossref","unstructured":"Schulz C Eger S Daxenberger J et al. Multi-task learning for argumentation mining in low-resource settings 2018. arXiv preprint arXiv:1804.04083.","DOI":"10.18653\/v1\/N18-2006"},{"key":"e_1_3_3_50_2","doi-asserted-by":"crossref","unstructured":"Cocarascu O Cabrio E Villata S et al. Dataset independent baselines for relation prediction in argument mining. In: Computational models of argument 2020 pp.45\u201352. IOS Press.","DOI":"10.3233\/FAIA200490"},{"key":"e_1_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Gemechu D Ruiz-Dolz R Reed C. Aries: a general benchmark for argument relation identification. In: 11th workshop on argument mining ArgMining 2024 2024 pp.1\u201314. Bangkok Thailand: Association for Computational Linguistics (ACL).","DOI":"10.18653\/v1\/2024.argmining-1.1"},{"key":"e_1_3_3_52_2","doi-asserted-by":"crossref","unstructured":"Kawarada M Hirao T Uchida W et al. Argument mining as a text-to-text generation task. In: Proceedings of the 18th conference of the European chapter of the association for computational linguistics (Volume 1: long papers) 2024 pp.2002\u20132014. St. Julian\u2019s Malta: Association for Computational Linguistics (ACL).","DOI":"10.18653\/v1\/2024.eacl-long.121"},{"key":"e_1_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Guo J Cheng L Zhang W et al. AQE: argument quadruplet extraction via a quad-tagging augmented generative approach 2023. arXiv preprint arXiv:2305.19902.","DOI":"10.18653\/v1\/2023.findings-acl.59"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","unstructured":"Chen G Cheng L Luu AT et al. Exploring the potential of large language models in computational argumentation. In: Ku L Martins A and Srikumar V (eds) Proceedings of the 62nd annual meeting of the association for computational linguistics (Volume 1: long papers) ACL 2024 Bangkok Thailand 11\u201316 August 2024 2024 pp.2309\u20132330. Bangkok Thailand: Association for Computational Linguistics. 10.18653\/v1\/2024.acl-long.126","DOI":"10.18653\/v1\/2024.acl-long.126"},{"key":"e_1_3_3_55_2","unstructured":"Abkenar MY Wang W Graupner H et al. Assessing open-source large language models on argumentation mining subtasks 2024. arXiv preprint arXiv:2411.05639."},{"key":"e_1_3_3_56_2","doi-asserted-by":"crossref","unstructured":"Mirzakhmedova N Gohsen M Chang CH et al. Are large language models reliable argument quality annotators? In: Conference on advances in robust argumentation machines 2024 pp.129\u2013146.\u00a0Cham Switzerland: Springer.","DOI":"10.1007\/978-3-031-63536-6_8"},{"key":"e_1_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Ruiz-Dolz R Lawrence J. Detecting argumentative fallacies in the wild: problems and limitations of large language models. In: Alshomary M Chen C Muresan S Park J and Romberg J (eds) Proceedings of the 10th workshop on argument mining ArgMining 2023 Singapore 7 December 2023 2023 pp.1\u201310. Singapore: Association for Computational Linguistics. 10.18653\/v1\/2023.argmining-1.1","DOI":"10.18653\/v1\/2023.argmining-1.1"},{"key":"e_1_3_3_58_2","doi-asserted-by":"crossref","unstructured":"Yeh MH Wan R Huang TH. Cocolofa: a dataset of news comments with common logical fallacies written by LLM-assisted crowds 2024. arXiv preprint arXiv:2410.03457.","DOI":"10.18653\/v1\/2024.emnlp-main.39"},{"key":"e_1_3_3_59_2","unstructured":"Cabessa J Hernault H Mushtaq U. In-context learning and fine-tuning GPT for argument mining 2024. arXiv preprint arXiv:2406.06699."},{"key":"e_1_3_3_60_2","doi-asserted-by":"crossref","unstructured":"Li H Wu Y Schlegel V et al. Which side are you on? A multi-task dataset for end-to-end argument summarisation and evaluation 2024. arXiv preprint arXiv:2406.03151.","DOI":"10.18653\/v1\/2024.findings-acl.9"},{"key":"e_1_3_3_61_2","doi-asserted-by":"crossref","unstructured":"Boltu\u017ei\u0107 F \u0160najder J. Back up your stance: Recognizing arguments in online discussions. In: Proceedings of the first workshop on argumentation mining 2014 pp.49\u201358. Gothenburg Sweden: Association for Computational Linguistics (ACL).","DOI":"10.3115\/v1\/W14-2107"},{"key":"e_1_3_3_62_2","doi-asserted-by":"crossref","unstructured":"Thorne J Vlachos A Christodoulopoulos C et al. Fever: a large-scale dataset for fact extraction and verification 2018. arXiv preprint arXiv:1803.05355.","DOI":"10.18653\/v1\/N18-1074"},{"key":"e_1_3_3_63_2","doi-asserted-by":"crossref","unstructured":"Cheng L Bing L He R et al. IAM: a comprehensive and large-scale dataset for integrated argument mining tasks 2022. arXiv preprint arXiv:2203.12257.","DOI":"10.18653\/v1\/2022.acl-long.162"},{"key":"e_1_3_3_64_2","doi-asserted-by":"crossref","unstructured":"Bar-Haim R Bhattacharya I Dinuzzo F et al. Stance classification of context-dependent claims. In: Proceedings of the 15th conference of the European chapter of the association for computational linguistics: volume 1 long papers 2017 pp.251\u2013261. Valencia Spain: Association for Computational Linguistics.","DOI":"10.18653\/v1\/E17-1024"},{"key":"e_1_3_3_65_2","doi-asserted-by":"crossref","unstructured":"Aharoni E Polnarov A Lavee T et al. A benchmark dataset for automatic detection of claims and evidence in the context of controversial topics. In: Proceedings of the first workshop on argumentation mining 2014 pp.64\u201368. Baltimore Maryland USA: Association for Computational Linguistics.","DOI":"10.3115\/v1\/W14-2109"},{"key":"e_1_3_3_66_2","unstructured":"Levy R Bogin B Gretz S et al. Towards an argumentative content search engine using weak supervision. In: Proceedings of the 27th international conference on computational linguistics 2018 pp.2066\u20132081. Santa Fe New Mexico USA: Association for Computational Linguistics."},{"key":"e_1_3_3_67_2","doi-asserted-by":"crossref","unstructured":"Shnarch E Alzate C Dankin L et al. Will it blend? Blending weak and strong labeled data in a neural network for argumentation mining. In: Proceedings of the 56th annual meeting of the association for computational linguistics (Volume 2: short papers) 2018 pp.599\u2013605. Association for Computational Linguistics Melbourne Australia.","DOI":"10.18653\/v1\/P18-2095"},{"key":"e_1_3_3_68_2","doi-asserted-by":"crossref","unstructured":"Shnarch E Choshen L Moshkowich G et al. Unsupervised expressive rules provide explainability and assist human experts grasping new domains 2020. arXiv preprint arXiv:2010.09459.","DOI":"10.18653\/v1\/2020.findings-emnlp.243"},{"key":"e_1_3_3_69_2","unstructured":"Peldszus A Stede M. An annotated corpus of argumentative microtexts. In: Argumentation and reasoned action: proceedings of the 1st European conference on argumentation Lisbon Volume 2 2015 pp.801\u2013815. London UK: College Publications."},{"key":"e_1_3_3_70_2","doi-asserted-by":"crossref","unstructured":"Skeppstedt M Peldszus A Stede M. More or less controlled elicitation of argumentative text: enlarging a microtext corpus via crowdsourcing. In: Proceedings of the 5th workshop on argument mining 2018 pp.155\u2013163. Brussels Belgium: Association for Computational Linguistics.","DOI":"10.18653\/v1\/W18-5218"},{"key":"e_1_3_3_71_2","doi-asserted-by":"crossref","unstructured":"Cabrio E Villata S. Node: a benchmark of natural language arguments. In: Computational models of argument 2014 pp.449\u2013450.\u00a0Amsterdam The Netherlands: IOS Press.","DOI":"10.3233\/978-1-61499-436-7-449"},{"key":"e_1_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00295"},{"key":"e_1_3_3_73_2","unstructured":"He P Liu X Gao J et al. Deberta: decoding-enhanced BERT with disentangled attention. In: 9th international conference on learning representations ICLR 2021 virtual event Austria 3\u20137 May 2021 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=XPZIaotutsD."},{"key":"e_1_3_3_74_2","doi-asserted-by":"crossref","unstructured":"Goddard C Siriwardhana S Ehghaghi M et al. Arcee\u2019s MergeKit: a toolkit for merging large language models. In: Dernoncourt F Preo\u0163iuc-Pietro D and Shimorina A (eds) Proceedings of the 2024 conference on empirical methods in natural language processing: industry track 2024 pp.477\u2013485. Miami Florida US: Association for Computational Linguistics. https:\/\/aclanthology.org\/2024.emnlp-industry.36.","DOI":"10.18653\/v1\/2024.emnlp-industry.36"},{"key":"e_1_3_3_75_2","unstructured":"Deep PT Bhardwaj R Poria S. Della-merging: reducing interference in model merging through magnitude-based sampling 2024. arXiv preprint arXiv:2406.11617."},{"key":"e_1_3_3_76_2","unstructured":"Ilharco G Ribeiro MT Wortsman M et al. Editing models with task arithmetic 2022. arXiv preprint arXiv:2212.04089."},{"key":"e_1_3_3_77_2","first-page":"7093","article-title":"Ties-merging: resolving interference when merging models","volume":"36","author":"Yadav P","year":"2023","unstructured":"Yadav P, Tam D, Choshen L, et al. Ties-merging: resolving interference when merging models. Adv Neural Inf Process Syst 2023; 36: 7093\u20137115.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_78_2","unstructured":"Yu L Yu B Yu H et al. Language models are super mario: absorbing abilities from homologous models as a free lunch. In: Forty-first international conference on machine learning ICML 2024 Vienna Austria 21\u201327 July 2024 2024. Vienna Austria: Association for Computing Machinery\/PMLR (for the proceedings) OpenReview.net. https:\/\/openreview.net\/forum?id=fq0NaiU8Ex."},{"key":"e_1_3_3_79_2","unstructured":"Lin CY. ROUGE: a package for automatic evaluation of summaries. In: Text summarization branches out 2004 pp.74\u201381. Barcelona Spain: Association for Computational Linguistics. https:\/\/aclanthology.org\/W04-1013\/."},{"key":"e_1_3_3_80_2","unstructured":"Denkowski M Lavie A. Meteor 1.3: automatic metric for reliable optimization and evaluation of machine translation systems. In: Proceedings of the sixth workshop on statistical machine translation 2011 pp.85\u201391. Edinburgh Scotland UK: Association for Computational Linguistics."},{"key":"e_1_3_3_81_2","unstructured":"Zhang T Kishore V Wu F et al. Bertscore: evaluating text generation with bert 2019. arXiv preprint arXiv:1904.09675."},{"key":"e_1_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888911000166"}],"container-title":["Argument &amp; Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/19462174251413169","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/19462174251413169","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/19462174251413169","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T11:53:31Z","timestamp":1777377211000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/19462174251413169"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":81,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1177\/19462174251413169"],"URL":"https:\/\/doi.org\/10.1177\/19462174251413169","relation":{},"ISSN":["1946-2166","1946-2174"],"issn-type":[{"value":"1946-2166","type":"print"},{"value":"1946-2174","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,28]]}}}