{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:52:59Z","timestamp":1743130379146,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031635359"},{"type":"electronic","value":"9783031635366"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T00:00:00Z","timestamp":1721174400000},"content-version":"vor","delay-in-days":198,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Decision-making and opinion formation are influenced by arguments from various online sources, including social media, web publishers, and, not least, the search engines used to retrieve them. However, many, if not most, arguments on the web are informal, especially in online discussions or on personal pages. They can be long and unstructured, subjective and emotional, and contain inappropriate language. This makes it difficult to find relevant arguments efficiently. We hypothesize that, on search engine results pages, \u201cobjective snippets\u201d of arguments are better suited than the commonly used extractive snippets and develop corresponding methods for two important tasks:<jats:italic>snippet generation<\/jats:italic>and<jats:italic>neutralization<\/jats:italic>. For each of these tasks, we investigate two approaches based on (1)\u00a0prompt engineering for large language models\u00a0(LLMs), and (2)\u00a0supervised models trained on existing datasets. We find that a supervised summarization model outperforms zero-shot summarization with LLMs for snippet generation. For neutralization, using reinforcement learning to align an LLM with human preferences for suitable arguments leads to the best results. Both tasks are complementary, and their combination leads to the best snippets of arguments according to automatic and human evaluation.<\/jats:p>","DOI":"10.1007\/978-3-031-63536-6_20","type":"book-chapter","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T05:01:50Z","timestamp":1721106110000},"page":"335-351","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Objective Argument Summarization in\u00a0Search"],"prefix":"10.1007","author":[{"given":"Timon","family":"Ziegenbein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shahbaz","family":"Syed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Potthast","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henning","family":"Wachsmuth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,17]]},"reference":[{"key":"20_CR1","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-030-30179-8_4","volume-title":"KI 2019: Advances in Artificial Intelligence","author":"Y Ajjour","year":"2019","unstructured":"Ajjour, Y., Wachsmuth, H., Kiesel, J., Potthast, M., Hagen, M., Stein, B.: Data acquisition for argument search: the args.me corpus. In: Benzm\u00fcller, C., Stuckenschmidt, H. (eds.) KI 2019. LNCS (LNAI), vol. 11793, pp. 48\u201359. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-30179-8_4"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Alshomary, M., D\u00fcsterhus, N., Wachsmuth, H.: Extractive snippet generation for arguments. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, Virtual Event, China, 25\u201330 July 2020, pp. 1969\u20131972. ACM (2020). https:\/\/doi.org\/10.1145\/3397271.3401186","DOI":"10.1145\/3397271.3401186"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Bando, L.L., Scholer, F., Turpin, A.: Constructing query-biased summaries: a comparison of human and system generated snippets. In: Proceedings of the Third Symposium on Information Interaction in Context, pp. 195\u2013204 (2010)","DOI":"10.1145\/1840784.1840813"},{"key":"20_CR4","doi-asserted-by":"crossref","unstructured":"Bar-Haim, R., Eden, L., Friedman, R., Kantor, Y., Lahav, D., Slonim, N.: From arguments to key points: towards automatic argument summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5\u201310 July 2020, pp. 4029\u20134039. Association for Computational Linguistics (2020). https:\/\/www.aclweb.org\/anthology\/2020.acl-main.371\/","DOI":"10.18653\/v1\/2020.acl-main.371"},{"key":"20_CR5","unstructured":"Cao, Z., Wei, F., Li, W., Li, S.: Faithful to the original: fact aware neural abstractive summarization. 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. 4784\u20134791, AAAI Press (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16121"},{"key":"20_CR6","unstructured":"Chen, P., Wu, F., Wang, T., Ding, W.: A semantic QA-based approach for text summarization evaluation. In: McIlraith, S.A., Weinberger, K.Q. (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, pp. 4800\u20134807, AAAI Press (2018). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI18\/paper\/view\/16115"},{"key":"20_CR7","doi-asserted-by":"publisher","unstructured":"Chen, W., Syed, S., Stein, B., Hagen, M., Potthast, M.: Abstractive snippet generation. In: Huang, Y., King, I., Liu, T., van Steen, M. (eds.) WWW 2020: The Web Conference 2020, Taipei, Taiwan, 20\u201324 April 2020, pp. 1309\u20131319. ACM \/ IW3C2 (2020). https:\/\/doi.org\/10.1145\/3366423.3380206. https:\/\/doi.org\/10.1145\/3366423.3380206","DOI":"10.1145\/3366423.3380206 10.1145\/3366423.3380206"},{"key":"20_CR8","doi-asserted-by":"publisher","unstructured":"Chen, W.F., Al\u00a0Khatib, K., Stein, B., Wachsmuth, H.: Controlled neural sentence-level reframing of news articles. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.T. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 2683\u20132693, Association for Computational Linguistics, Punta Cana, Dominican Republic, November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.228. https:\/\/aclanthology.org\/2021.findings-emnlp.228","DOI":"10.18653\/v1\/2021.findings-emnlp.228"},{"key":"20_CR9","unstructured":"Croft, W.B., Metzler, D., Strohman, T.: Search Engines: Information Retrieval in Practice, vol. 520. Addison-Wesley Reading (2010)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Dai, N., Liang, J., Qiu, X., Huang, X.: Style transformer: unpaired text style transfer without disentangled latent representation. arXiv:1905.05621 [cs] (2019)","DOI":"10.18653\/v1\/P19-1601"},{"key":"20_CR11","unstructured":"Dang, H.T.: Overview of DUC 2005. In: Proceedings of the Document Understanding Conference, vol. 2005, pp. 1\u201312 (2005)"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Gero, K., Kedzie, C., Reeve, J., Chilton, L.: Low level linguistic controls for style transfer and content preservation. In: Proceedings of the 12th International Conference on Natural Language Generation, pp. 208\u2013218 (2019)","DOI":"10.18653\/v1\/W19-8628"},{"key":"20_CR13","doi-asserted-by":"publisher","unstructured":"Goyal, T., Li, J.J., Durrett, G.: News summarization and evaluation in the era of GPT-3. CoRR abs\/2209.12356 (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.12356","DOI":"10.48550\/arXiv.2209.12356"},{"key":"20_CR14","unstructured":"Groeneveld, D., Meyerzon, D., Mowatt, D.: Generating search result summaries, uS Patent 7,853,587 (2010)"},{"key":"20_CR15","unstructured":"Hu, E.J., et al.: LoRA: low-rank adaptation of large language models. In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, 25\u201329 April 2022, OpenReview.net (2022). https:\/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"20_CR16","unstructured":"Hu, Z., Yang, Z., Liang, X., Salakhutdinov, R., Xing, E.P.: Toward controlled generation of text. In: Proceedings of the 34th International Conference on Machine Learning, vol.\u00a070, pp. 1587\u20131596 (2017)"},{"key":"20_CR17","doi-asserted-by":"publisher","unstructured":"Jin, D., Jin, Z., Hu, Z., Vechtomova, O., Mihalcea, R.: Deep learning for text style transfer: a survey. Comput. Linguistics (1), 155\u2013205 (2022). https:\/\/doi.org\/10.1162\/COLI_A_00426","DOI":"10.1162\/COLI_A_00426"},{"key":"20_CR18","doi-asserted-by":"crossref","unstructured":"Kabbara, J., Cheung, J.C.K.: Stylistic transfer in natural language generation systems using recurrent neural networks. In: Proceedings of the Workshop on Uphill Battles in Language Processing, pp. 43\u201347 (2016)","DOI":"10.18653\/v1\/W16-6010"},{"key":"20_CR19","unstructured":"Kendall, M.G.: Rank Correlation Methods (1948)"},{"key":"20_CR20","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1177\/001316447003000105","volume":"1","author":"K Krippendorff","year":"1970","unstructured":"Krippendorff, K.: Estimating the reliability, systematic error and random error of interval data. Educ. Psychol. Measur. 1, 61\u201370 (1970)","journal-title":"Educ. Psychol. Measur."},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5\u201310 July 2020, pp. 7871\u20137880. Association for Computational Linguistics (2020). https:\/\/www.aclweb.org\/anthology\/2020.acl-main.703\/","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"20_CR22","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain, July 2004. https:\/\/www.aclweb.org\/anthology\/W04-1013"},{"key":"20_CR23","doi-asserted-by":"publisher","unstructured":"Madanagopal, K., Caverlee, J.: Reinforced sequence training based subjective bias correction. In: Vlachos, A., Augenstein, I. (eds.) Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, pp. 2585\u20132598. Association for Computational Linguistics, Dubrovnik, Croatia, May 2023. https:\/\/doi.org\/10.18653\/v1\/2023.eacl-main.189. https:\/\/aclanthology.org\/2023.eacl-main.189","DOI":"10.18653\/v1\/2023.eacl-main.189"},{"key":"20_CR24","doi-asserted-by":"publisher","unstructured":"Maynez, J., Narayan, S., Bohnet, B., McDonald, R.T.: On faithfulness and factuality in abstractive summarization. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J.R. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Online, 5\u201310 July 2020, pp. 1906\u20131919. Association for Computational Linguistics (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.173","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"20_CR25","doi-asserted-by":"publisher","unstructured":"Nallapati, R., Zhou, B., dos Santos, C.N., G\u00fcl\u00e7ehre, \u00c7., Xiang, B.: Abstractive text summarization using sequence-to-sequence RNNs and beyond. In: Goldberg, Y., Riezler, S. (eds.) Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, CoNLL 2016, Berlin, Germany, 11\u201312 August 2016, pp. 280\u2013290. ACL (2016). https:\/\/doi.org\/10.18653\/v1\/k16-1028","DOI":"10.18653\/v1\/k16-1028"},{"key":"20_CR26","unstructured":"Page, L., Brin, S., Motwani, R., Winograd, T.: The PageRank citation ranking: bringing order to the web. Technical report, Stanford InfoLab (1999)"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Pryzant, R., Martinez, R.D., Dass, N., Kurohashi, S., Jurafsky, D., Yang, D.: Automatically neutralizing subjective bias in text. In: Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, pp. 480\u2013489 (2020)","DOI":"10.1609\/aaai.v34i01.5385"},{"key":"20_CR28","doi-asserted-by":"publisher","unstructured":"Stab, C., et al.: ArgumenText: searching for arguments in heterogeneous sources. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, pp. 21\u201325. Association for Computational Linguistics, New Orleans, Louisiana, June 2018. https:\/\/doi.org\/10.18653\/v1\/N18-5005. https:\/\/www.aclweb.org\/anthology\/N18-5005","DOI":"10.18653\/v1\/N18-5005"},{"key":"20_CR29","unstructured":"Stiennon, N., et al.: Learning to summarize from human feedback. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020, Curran Associates Inc., Red Hook, NY, USA (2020). ISBN 9781713829546"},{"key":"20_CR30","doi-asserted-by":"publisher","unstructured":"Syed, S., Khatib, K.A., Alshomary, M., Wachsmuth, H., Potthast, M.: Generating informative conclusions for argumentative texts. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Findings of the Association for Computational Linguistics: ACL\/IJCNLP 2021, Online Event, 1\u20136 August 2021, Findings of ACL, vol. ACL\/IJCNLP 2021, pp. 3482\u20133493. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-acl.306","DOI":"10.18653\/v1\/2021.findings-acl.306"},{"key":"20_CR31","unstructured":"Taori, R., et al.: Stanford Alpaca: an instruction-following LLaMA model (2023). https:\/\/github.com\/tatsu-lab\/stanford_alpaca"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Tombros, A., Sanderson, M.: Advantages of Query Biased Summaries in Information Retrieval. In: Proceedings of SIGIR 1998, pp. 2\u201310 (1998)","DOI":"10.1145\/290941.290947"},{"key":"20_CR33","doi-asserted-by":"publisher","unstructured":"Wachsmuth, H., et al.: Building an argument search engine for the web. In: Proceedings of the 4th Workshop on Argument Mining, pp. 49\u201359. Association for Computational Linguistics, Copenhagen, Denmark, September 2017. https:\/\/doi.org\/10.18653\/v1\/W17-5106. https:\/\/www.aclweb.org\/anthology\/W17-5106","DOI":"10.18653\/v1\/W17-5106"},{"key":"20_CR34","unstructured":"Walker, M.: Information and deliberation in discourse. In: Intentionality and Structure in Discourse Relations (1993). https:\/\/aclanthology.org\/W93-0238"},{"key":"20_CR35","doi-asserted-by":"crossref","unstructured":"White, R., Ruthven, I., Jose, J.M.: Web document summarization: a task-oriented evaluation. In: 12th International Workshop on Database and Expert Systems Applications, pp. 951\u2013955. IEEE (2001)","DOI":"10.1109\/DEXA.2001.953177"},{"key":"20_CR36","unstructured":"Zhang, J., Zhao, Y., Saleh, M., Liu, P.J.: PEGASUS: pre-training with extracted gap-sentences for abstractive summarization. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event, Proceedings of Machine Learning Research, vol. 119, pp. 11328\u201311339. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/zhang20ae.html"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Ziegenbein, T., Skitalinskaya, G., Makou, A.B., Wachsmuth, H.: LLM-based rewriting of inappropriate argumentation using reinforcement learning (2024)","DOI":"10.18653\/v1\/2024.acl-long.244"},{"key":"20_CR38","doi-asserted-by":"publisher","unstructured":"Ziegenbein, T., Syed, S., Lange, F., Potthast, M., Wachsmuth, H.: Modeling appropriate language in argumentation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL), pp. 4344\u20134363. Association for Computational Linguistics, July 2023. https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.238. https:\/\/aclanthology.org\/2023.acl-long.238.pdf","DOI":"10.18653\/v1\/2023.acl-long.238"},{"key":"20_CR39","unstructured":"Ziegler, D.M., et al.: Fine-tuning language models from human preferences. CoRR (2019). http:\/\/arxiv.org\/abs\/1909.08593"}],"container-title":["Lecture Notes in Computer Science","Robust Argumentation Machines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-63536-6_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,24]],"date-time":"2024-11-24T06:00:13Z","timestamp":1732428013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-63536-6_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031635359","9783031635366"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-63536-6_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"RATIO","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Conference on Advances in Robust Argumentation Machines","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bielefeld","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ratio2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ratio.sc.cit-ec.uni-bielefeld.de\/de\/home\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}