{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T18:42:42Z","timestamp":1770230562979,"version":"3.49.0"},"reference-count":46,"publisher":"Association for Computing Machinery (ACM)","issue":"11","funder":[{"DOI":"10.13039\/100000185","name":"DARPA","doi-asserted-by":"crossref","award":["HR001122C0029"],"award-info":[{"award-number":["HR001122C0029"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,11,30]]},"abstract":"<jats:p>\n                    Sociocultural norms serve as guiding principles for personal conduct in social interactions, emphasizing respect, cooperation, and appropriate behavior, which is able to benefit tasks including conversational information retrieval, contextual information retrieval, and retrieval-enhanced machine learning. We propose a scalable approach for constructing a Sociocultural Norm (\n                    <jats:sc>Scn<\/jats:sc>\n                    ) Base using large language models (LLMs) for socially aware dialogues. We construct a comprehensive and publicly accessible Chinese Sociocultural NormBase (\n                    <jats:sc>ChineseNormBase<\/jats:sc>\n                    ). Our approach utilizes socially aware dialogues, enriched with contextual frames, as the primary data source to constrain the generating process and reduce the hallucinations. This enables extracting of high-quality and nuanced natural-language norm statements, leveraging the pragmatic implications of utterances with respect to the situation. As real dialogue annotated with gold frames are not readily available, we propose using synthetic data. Our empirical results show (i) the quality of the\n                    <jats:sc>Scn<\/jats:sc>\n                    s derived from synthetic data is comparable to that from real dialogues annotated with gold frames, and (ii) the quality of the\n                    <jats:sc>Scn<\/jats:sc>\n                    s extracted from real data, annotated with either silver (predicted) or gold frames, surpasses that without the frame annotations. We further show the effectiveness of the extracted\n                    <jats:sc>Scn<\/jats:sc>\n                    s in a Retrieval-Augmented Generation (RAG)-based model to reason about multiple downstream dialogue tasks.\n                  <\/jats:p>","DOI":"10.1145\/3697838","type":"journal-article","created":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T09:25:22Z","timestamp":1728033922000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Scalable Frame-Based Construction of Sociocultural Norm Bases for Socially Aware Dialogues"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3825-5151","authenticated-orcid":false,"given":"Shilin","family":"Qu","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9578-819X","authenticated-orcid":false,"given":"Weiqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6486-5639","authenticated-orcid":false,"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9628-5992","authenticated-orcid":false,"given":"Haolan","family":"Zhan","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9808-9992","authenticated-orcid":false,"given":"Zhuang","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7764-431X","authenticated-orcid":false,"given":"Lizhen","family":"Qu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0027-942X","authenticated-orcid":false,"given":"Linhao","family":"Luo","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4651-2821","authenticated-orcid":false,"given":"Yuan-Fang","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7326-8380","authenticated-orcid":false,"given":"Gholamreza","family":"Haffari","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Melbourne, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","unstructured":"Garima Agrawal Tharindu Kumarage Zeyad Alghami and Huan Liu. 2024. Can knowledge graphs reduce hallucinations in LLMs?: A survey. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) 3947\u20133960. DOI: 10.18653\/v1\/2024.naacl-long.219","DOI":"10.18653\/v1\/2024.naacl-long.219"},{"key":"e_1_3_2_3_1","doi-asserted-by":"crossref","first-page":"3468","DOI":"10.1145\/3539618.3591925","volume-title":"Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"Bendersky Michael","year":"2023","unstructured":"Michael Bendersky, Danqi Chen, Fernando Diaz, and Hamed Zamani. 2023. SIGIR 2023 workshop on retrieval enhanced machine learning. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. ACM, 3468\u20133471."},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"e_1_3_2_5_1","first-page":"75","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","volume":"11","author":"Blass Joseph","year":"2015","unstructured":"Joseph Blass and Ian Horswill. 2015. Implementing injunctive social norms using defeasible reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, Vol. 11, 75\u201381."},{"key":"e_1_3_2_6_1","unstructured":"Yiming Cui Wanxiang Che Ting Liu Bing Qin Shijin Wang and Guoping Hu. 2020. Revisiting pre-trained models for Chinese natural language processing. In Findings of the Association for Computational Linguistics: EMNLP 2020 657\u2013668."},{"key":"e_1_3_2_7_1","first-page":"3455","volume-title":"Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201922)","author":"Dalton Jeffrey","year":"2022","unstructured":"Jeffrey Dalton, Sophie Fischer, Paul Owoicho, Filip Radlinski, Federico Rossetto, Johanne R. Trippas, and Hamed Zamani. 2022. Conversational information seeking: Theory and application. In Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR \u201922). ACM, 3455\u20133458."},{"key":"e_1_3_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462806"},{"key":"e_1_3_2_9_1","volume-title":"Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC \u201918)","author":"Elsahar Hady","year":"2018","unstructured":"Hady Elsahar, Pavlos Vougiouklis, Arslen Remaci, Christophe Gravier, Jonathon Hare, Frederique Laforest, and Elena Simperl. 2018. T-REx: A large scale alignment of natural language with knowledge base triples. In Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC \u201918)."},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.101"},{"key":"e_1_3_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.48"},{"key":"e_1_3_2_12_1","doi-asserted-by":"crossref","first-page":"15217","DOI":"10.18653\/v1\/2023.emnlp-main.941","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Fung Yi","year":"2023","unstructured":"Yi Fung, Tuhin Chakrabarty, Hao Guo, Owen Rambow, Smaranda Muresan, and Heng Ji. 2023. NORMSAGE: Multi-lingual multi-cultural norm discovery from conversations on-the-fly. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.Houda Bouamor, Juan Pino, and Kalika Bali (Eds.), Association for Computational Linguistics, 15217\u201315230. Retrieved from https:\/\/aclanthology.org\/2023.emnlp-main.941"},{"key":"e_1_3_2_13_1","volume-title":"The Information Retrieval Series","author":"Gao Jianfeng","year":"2023","unstructured":"Jianfeng Gao, Chenyan Xiong, Paul Bennett, and Nick Craswell. 2023. Neural Approaches to Conversational Information Retrieval. The Information Retrieval Series, Vol. 44. Springer."},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","unstructured":"H. P. Grice. 1975. Logic and Conversation. Brill Leiden The Netherlands 41\u2013 58. DOI: 10.1163\/9789004368811_003","DOI":"10.1163\/9789004368811_003"},{"key":"e_1_3_2_15_1","first-page":"537","volume-title":"Proceedings of the 45th European Conference on Information Retrieval (ECIR \u201923)Lecture Notes in Computer Science","volume":"13980","author":"Hai Nam Le","unstructured":"Nam Le Hai, Thomas Gerald, Thibault Formal, Jian-Yun Nie, Benjamin Piwowarski, and Laure Soulier. [n.d.]. CoSPLADE: Contextualizing SPLADE for conversational information retrieval. In Proceedings of the 45th European Conference on Information Retrieval (ECIR \u201923). Lecture Notes in Computer Science, Vol. 13980, 537\u2013552."},{"key":"e_1_3_2_16_1","doi-asserted-by":"crossref","unstructured":"Janet Holmes and Nicholas Wilson. 2017. An Introduction to Sociolinguistics. Routledge Taylor and Francis Group.","DOI":"10.4324\/9781315728438"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.49"},{"key":"e_1_3_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3635153"},{"key":"e_1_3_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16792"},{"key":"e_1_3_2_20_1","first-page":"680","volume-title":"Proceedings of the 18th International Conference on Semantic Web (ESWC \u201921)","author":"Ilievski Filip","year":"2021","unstructured":"Filip Ilievski, Pedro Szekely, and Bin Zhang. 2021. CSKG: The commonsense knowledge graph. In Proceedings of the 18th International Conference on Semantic Web (ESWC \u201921). Springer, 680\u2013696."},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612088"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447846"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3610949"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219745"},{"key":"e_1_3_2_25_1","unstructured":"Patrick S. H. Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel Sebastian Riedel and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS \u201920). Hugo Larochelle Marc\u2019Aurelio Ranzato Raia Hadsell Maria-Florina Balcan and Hsuan-Tien Lin (Eds.) Neural Information Processing Systems Foundation Inc. (NeurIPS)."},{"key":"e_1_3_2_26_1","first-page":"15732","volume-title":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","author":"Li Oliver","year":"2023","unstructured":"Oliver Li, Mallika Subramanian, Arkadiy Saakyan, Sky CH-Wang, and Smaranda Muresan. 2023. NormDial: A comparable bilingual synthetic dialog dataset for modeling social norm adherence and violation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 15732\u201315744."},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","unstructured":"Deyin Liu Lin (Yuanbo) Wu Richang Hong Zongyuan Ge Jialie Shen Farid Boussaid and Mohammed Bennamoun. 2023. Generative metric learning for adversarially robust open-world person re-identification. ACM Trans. Multimedia Comput. Commun. Appl. 19 1 (Jan. 2023) Article 20 19 pages. DOI: 10.1145\/3522714","DOI":"10.1145\/3522714"},{"key":"e_1_3_2_28_1","doi-asserted-by":"crossref","unstructured":"Hugo Liu and Push Singh. 2004. ConceptNet\u2014A practical commonsense reasoning tool-kit. BT Technol. J. 22 4 (2004) 211\u2013226.","DOI":"10.1023\/B:BTTJ.0000047600.45421.6d"},{"key":"e_1_3_2_29_1","first-page":"4569","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP \u201920)","author":"Mostafazadeh Nasrin","year":"2020","unstructured":"Nasrin Mostafazadeh, Aditya Kalyanpur, Lori Moon, David Buchanan, Lauren Berkowitz, Or Biran, and Jennifer Chu-Carroll. 2020. GLUCOSE: GeneraLized and contextualized story explanations. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP \u201920), 4569\u20134586."},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.486"},{"key":"e_1_3_2_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1004"},{"key":"e_1_3_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210103"},{"key":"e_1_3_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.770"},{"key":"e_1_3_2_35_1","unstructured":"Karan Singhal Shekoofeh Azizi Tao Tu S. Sara Mahdavi Jason Wei Hyung Won Chung Nathan Scales Ajay Tanwani Heather Cole-Lewis Stephen Pfohl et al. 2023. Large language models encode clinical knowledge. Nature (2023) 1\u20139."},{"key":"e_1_3_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_37_1","unstructured":"Jiashuo Sun Chengjin Xu Lumingyuan Tang Saizhuo Wang Chen Lin Yeyun Gong Heung-Yeung Shum and Jian Guo. 2024. Think-on-graph: Deep and responsible reasoning of large language model with knowledge graph. In Proceedings of the International Conference on Learning Representations (ICLR \u201924)."},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","unstructured":"Yucheng Suo Zhedong Zheng Xiaohan Wang Bang Zhang and Yi Yang. 2024. Jointly harnessing prior structures and temporal consistency for sign language video generation. ACM Trans. Multimedia Comput. Commun. Appl. 20 6 (Mar. 2024) Article 185 18 pages. DOI: 10.1145\/3648368","DOI":"10.1145\/3648368"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1421"},{"key":"e_1_3_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591716"},{"key":"e_1_3_2_41_1","doi-asserted-by":"publisher","unstructured":"Xing Xu Yifan Wang Yixuan He Yang Yang Alan Hanjalic and Heng Tao Shen. 2021. Cross-modal hybrid feature fusion for image-sentence matching. ACM Trans. Multimedia Comput. Commun. Appl. 17 4 (Nov. 2021) Article 127 23 pages. DOI: 10.1145\/3458281","DOI":"10.1145\/3458281"},{"key":"e_1_3_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531722"},{"key":"e_1_3_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591877"},{"key":"e_1_3_2_44_1","doi-asserted-by":"publisher","unstructured":"Sheng Zhang Xiaodong Liu Jingjing Liu Jianfeng Gao Kevin Duh and Benjamin Van Durme. 2018. Record: Bridging the gap between human and machine commonsense reading comprehension. arXiv.1810.12885. Retrieved from 10.48550\/arXiv.1810.12885","DOI":"10.48550\/arXiv.1810.12885"},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","unstructured":"Zhedong Zheng Liang Zheng Michael Garrett Yi Yang Mingliang Xu and Yi-Dong Shen. 2020. Dual-path convolutional image-text embeddings with instance loss. ACM Trans. Multimedia Comput. Commun. Appl. 16 2 (May 2020) Article 51 23 pages. DOI: 10.1145\/3383184","DOI":"10.1145\/3383184"},{"key":"e_1_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.392"},{"key":"e_1_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.429"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3697838","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T15:10:24Z","timestamp":1762528224000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3697838"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":46,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11,30]]}},"alternative-id":["10.1145\/3697838"],"URL":"https:\/\/doi.org\/10.1145\/3697838","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]},"assertion":[{"value":"2024-04-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-13","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}