NormDial: A Comparable Bilingual Synthetic Dialog Dataset for Modeling Social Norm Adherence and Violation
Not on the map. Why?
Abstract (arXiv)
Social norms fundamentally shape interpersonal communication. We present NormDial, a high-quality dyadic dialogue dataset with turn-by-turn annotations of social norm adherences and violations for Chinese and American cultures. Introducing the task of social norm observance detection, our dataset is synthetically generated in both Chinese and English using a human-in-the-loop pipeline by prompting large language models with a small collection of expert-annotated social norms. We show that our generated dialogues are of high quality through human evaluation and further evaluate the performance of existing large language models on this task. Our findings point towards new directions for understanding the nuances of social norms as they manifest in conversational contexts that span across languages and cultures.
Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 23 Oct 2023.
Builds on
20 of 39 references.
References · 20
- 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,413
- 2021Ethical and social risks of harm from Language Modelscited by 957
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
- 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
- 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
- 2020Social Chemistry 101: Learning to Reason about Social and Moral Normscited by 253
- 2021Visually Grounded Reasoning across Languages and Culturescited by 188
- 2022SODA: Million-scale Dialogue Distillation with Social Commonsense Contextualizationcited by 166
- 2021Can Machines Learn Morality? The Delphi Experimentcited by 140
- 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
- 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 92
- 2018Event2Mind: Commonsense Inference on Events, Intents, and Reactionscited by 82
8 more
- 2023PLACES: Prompting Language Models for Social Conversation Synthesiscited by 72
- 2023NormBank: A Knowledge Bank of Situational Social Normscited by 60
- 2022NormSAGE: Multi-Lingual Multi-Cultural Norm Discovery from Conversations On-the-Flycited by 48
- 2023The Parrot Dilemma: Human-Labeled vs. LLM-augmented Data in Classification Taskscited by 35
- 2023Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailmentcited by 22
- 2020Dialogue Distillation: Open-Domain Dialogue Augmentation Using Unpaired Datacited by 20
- 2021DREAM: Improving Situational QA by First Elaborating the Situationcited by 18
- 2021Generative Conversational Networkscited by 11
Built on by
Citing papers per year: 2024: 8; 2025: 8; 2026: 8.
24 papers.
Sort:
By area:
- 2024Massively Multi-Cultural Knowledge Acquisition & LM Benchmarkingcited by 63
- 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 49
- 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Artcited by 26
- 2024Cultural Commonsense Knowledge for Intercultural Dialoguescited by 20
- 2025Multiple LLM Agents Debate for Equitable Cultural Alignmentcited by 20
- 2024CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Modelscited by 16
- 2025We Politely Insist: Your LLM Must Learn the Persian Art of Taarofcited by 6
- 2025Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Promptscited by 5
- 2025Isolating Culture Neurons in Multilingual Large Language Modelscited by 4
- 2025VideoNorms: Benchmarking Cultural Awareness of Video Language Modelscited by 4
- 2025MINDS: A Cross-cultural Dialogue Corpus for Social Norm Classification and Adherence Detectioncited by 4
- 2024Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialoguescited by 3
12 more
- 2025Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Benchcited by 3
- 2024LLM-Human Pipeline for Cultural Context Grounding of Conversationscited by 2
- 2025NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recoverycited by 2
- 2024Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialoguescited by 1
- 2026All Required, In Order: Phase-Level Evaluation for AI-Human Dialogue in Healthcare and Beyondcited by 1
- 2026AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Modelscited by 0
- 2026Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interactioncited by 0
- 2026EUDAIMONIA: Evaluating Undesirable Dynamics in AIcited by 0
- 2026PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgmentscited by 0
- 2026Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communitiescited by 0
- 2026Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understandingcited by 0
- 2026FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditingcited by 0
- 2026FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing21 Sep 2026
- 2026Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding10 Sep 2026
- 2026Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities29 Aug 2026
- 2026PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments27 Aug 2026
- 2026EUDAIMONIA: Evaluating Undesirable Dynamics in AI28 May 2026
- 2026Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction17 Mar 2026
- 2026AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models9 Mar 2026
- 2026All Required, In Order: Phase-Level Evaluation for AI-Human Dialogue in Healthcare and Beyond13 Jan 2026
- 2025MINDS: A Cross-cultural Dialogue Corpus for Social Norm Classification and Adherence Detection13 Nov 2025
- 2025VideoNorms: Benchmarking Cultural Awareness of Video Language Models9 Oct 2025
- 2025NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recovery22 Sep 2025
- 2025We Politely Insist: Your LLM Must Learn the Persian Art of Taarof1 Sep 2025
12 more
- 2025Isolating Culture Neurons in Multilingual Large Language Models4 Aug 2025
- 2025Multiple LLM Agents Debate for Equitable Cultural Alignment30 May 2025
- 2025Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts19 Apr 2025
- 2025Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Bench1 Apr 2025
- 2024LLM-Human Pipeline for Cultural Context Grounding of Conversations17 Oct 2024
- 2024Scalable Frame-based Construction of Sociocultural NormBases for Socially-Aware Dialogues4 Oct 2024
- 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art6 Jun 2024
- 2024CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Models22 May 2024
- 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers7 Apr 2024
- 2024Cultural Commonsense Knowledge for Intercultural Dialogues16 Feb 2024
- 2024Massively Multi-Cultural Knowledge Acquisition & LM Benchmarking14 Feb 2024
- 2024Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialogues17 Jan 2024
- 2025Multiple LLM Agents Debate for Equitable Cultural Alignmentcited by 20
- 2025Multiple LLM Agents Debate for Equitable Cultural Alignment30 May 2025
- 2024Massively Multi-Cultural Knowledge Acquisition & LM Benchmarkingcited by 63
- 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Artcited by 26
- 2024Cultural Commonsense Knowledge for Intercultural Dialoguescited by 20
- 2024CIVICS: Building a Dataset for Examining Culturally-Informed Values in Large Language Modelscited by 16
- 2025We Politely Insist: Your LLM Must Learn the Persian Art of Taarofcited by 6
- 2025Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Promptscited by 5
- 2025Isolating Culture Neurons in Multilingual Large Language Modelscited by 4
- 2025VideoNorms: Benchmarking Cultural Awareness of Video Language Modelscited by 4
- 2024Learning from Implicit User Feedback, Emotions and Demographic Information in Task-Oriented and Document-Grounded Dialoguescited by 3
- 2025Can LLMs Grasp Implicit Cultural Values? Benchmarking LLMs' Cultural Intelligence with CQ-Benchcited by 3
- 2024LLM-Human Pipeline for Cultural Context Grounding of Conversationscited by 2
- 2025NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recoverycited by 2
12 most cited of 21 All 21 (JSON)
- 2026FineWeb-CLaR: Culture, Language, and Region Annotations for Benchmark-Aligned Corpus Auditing21 Sep 2026
- 2026Whisper-Based Speech Transcription from Videos Across Multiple Languages for Cross-Cultural Understanding10 Sep 2026
- 2026Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities29 Aug 2026
- 2026PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments27 Aug 2026
- 2026EUDAIMONIA: Evaluating Undesirable Dynamics in AI28 May 2026
- 2026Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction17 Mar 2026
- 2026AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models9 Mar 2026
- 2026All Required, In Order: Phase-Level Evaluation for AI-Human Dialogue in Healthcare and Beyond13 Jan 2026
- 2025VideoNorms: Benchmarking Cultural Awareness of Video Language Models9 Oct 2025
- 2025NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recovery22 Sep 2025
- 2025We Politely Insist: Your LLM Must Learn the Persian Art of Taarof1 Sep 2025
- 2025Isolating Culture Neurons in Multilingual Large Language Models4 Aug 2025
12 newest of 21 All 21 (JSON)