Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships
David Jurgens, Agrima Seth, Jackson Sargent, Athena Aghighi, Michael Geraci
摘要
Understanding interpersonal communication requires, in part, understanding the social context and norms in which a message is said. However, current methods for identifying offensive content in such communication largely operate independent of context, with only a few approaches considering community norms or prior conversation as context. Here, we introduce a new approach to identifying inappropriate communication by explicitly modeling the social relationship between the individuals. We introduce a new dataset of contextually-situated judgments of appropriateness and show that large language models can readily incorporate relationship information to accurately identify appropriateness in a given context. Using data from online conversations and movie dialogues, we provide insight into how the relationships themselves function as implicit norms and quantify the degree to which context-sensitivity is needed in different conversation settings. Further, we also demonstrate that contextual-appropriateness judgments are predictive of other social factors expressed in language such as condescension and politeness.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET BenchmarkMinje Choi, Jiaxin Pei, Sagar Kumar, Chang Shu 等EMNLP 2023 · 被引用 36 次
- Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean DialoguesEunsu Kim, Junyeong Park, Juhyun Oh, Kiwoong Park 等ACL 2026 · 被引用 3 次
- User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive ScenariosXiaoyuan Wu, Roshni Kaushik, Wenkai Li, Lujo Bauer 等ACL 2026 · 被引用 2 次
它引用的顶会 Paper5
- MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained TransformersWenhui Wang, Furu Wei, Li Dong, Hangbo Bao 等NeurIPS 2020 · 被引用 2,727 次
- Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context LearningHaokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta 等NeurIPS 2022 · 被引用 1,483 次
- DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding SharingPengcheng He, Jianfeng Gao, Weizhu ChenICLR 2023 · 被引用 394 次
- Unifying Data Perspectivism and Personalization: An Application to Social NormsJoan Plepi, Béla Neuendorf, Lucie Flek, Charles WelchEMNLP 2022 · 被引用 4 次
- PRIDE: Predicting Relationships in ConversationsAnna Tigunova, Paramita Mirza, Andrew Yates, Gerhard WeikumEMNLP 2021
相关 Paper
- Quantifying Intimacy in LanguageJiaxin Pei, David JurgensEMNLP 2020 · 被引用 44 次
- Words Like Knives: Backstory-Personalized Modeling and Detection of Violent CommunicationJocelyn J. Shen, Akhila Yerukola, Xuhui Zhou, Cynthia Breazeal 等EMNLP 2025 · 被引用 4 次
- Please note that I'm just an AI: Analysis of Behavior Patterns of LLMs in (Non-)offensive Speech IdentificationEsra Dönmez, Thang Vu, Agnieszka FalenskaEMNLP 2024 · 被引用 1 次
- Feeling Rules in Language Models: Mapping Norms of Emotional Appropriateness Across Roles, Institutions, and IntensityGuangrui Fan, Dandan Liu, Aznul Qalid Md Sabri, Rui Zhang 等ACL 2026
- Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal GesturesAkhila Yerukola, Saadia Gabriel, Nanyun Peng, Maarten SapACL 2025 · 被引用 3 次
