NORMSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Fly

Knowledge of norms is needed to understand and reason about acceptable behavior in human communication and interactions across sociocultural scenarios. Most computational research on norms has focused on a single culture, and manually built datasets, from nonconversational settings. We address these limitations by proposing a new framework, NORMSAGE 1 , to automatically extract culturespecific norms from multi-lingual conversations. NORMSAGE uses GPT-3 prompting to 1) extract candidate norms directly from conversations and 2) provide explainable selfverification to ensure correctness and relevance. Comprehensive empirical results show the promise of our approach to extract highquality culture-aware norms from multi-lingual conversations (English and Chinese), across several quality metrics. Further, our relevance verification can be extended to assess the adherence and violation of any norm with respect to a conversation on-the-fly, along with textual explanation. NORMSAGE achieves an AUC of 94.6% in this grounding setup, with generated explanations matching human-written quality. 𝐚) 𝐈𝐧𝐢𝐭𝐢𝐚𝐥 𝐃𝐢𝐬𝐜𝐨𝐯𝐞𝐫𝒚: 𝒅𝒗𝒓(⋅) irrelevant contradict entail Correctness Verdict ( ! 𝑪 𝒗 ): Correctness Explanation ( ! 𝑪 𝒆 ): Yes, honesty is the foundation of trust, and strong family relationships are built on trust. Yes (correct) No (Incorrect) Xdial norm … Xdial norm Eddie: Yeah, but I'm still hungry. Jessica: Oh, okay. How you like the xiaolongbao I pack you? Eddie: It was really good. Jessica: Liar. I did not pack xiaolongbao! Eddie: Okay. Fine. I threw my lunch away. b) 𝐒𝐞𝐥𝐟-𝐕𝐞𝐫𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧: 𝐂𝐨𝐫𝐫𝐞𝐜𝐭𝐧𝐞𝐬𝐬 𝒄𝒐𝒓 ⋅ 𝐆𝐫𝐨𝐮𝐧𝐝𝐢𝐧𝐠 𝒈𝒓𝒅(⋅) NormsKB Population (filter out incorrect) Grounding Verdict ( ! 𝑮 𝒗 ): Grounding Explanation ( ! 𝑮 𝒆 ): The conversation contradicts the norm. Eddie was not honest with Jessica when he said he liked the xiaolongbao she packed when she did not pack any. (filter out irrelevant) + It is good to be honest with your family.