Social Bias Frames: Reasoning about Social and Power Implications of Language
Maarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky, Noah A. Smith, Yejin Choi
Abstract
Warning: this paper contains content that may be offensive or upsetting. Language has the power to reinforce stereotypes and project social biases onto others. At the core of the challenge is that it is rarely what is stated explicitly, but rather the implied meanings, that frame people's judgments about others. For example, given a statement that "we shouldn't lower our standards to hire more women," most listeners will infer the implicature intended by the speaker -that "women (candidates) are less qualified." Most semantic formalisms, to date, do not capture such pragmatic implications in which people express social biases and power differentials in language. We introduce SOCIAL BIAS FRAMES, a new conceptual formalism that aims to model the pragmatic frames in which people project social biases and stereotypes onto others. In addition, we introduce the Social Bias Inference Corpus to support large-scale modelling and evaluation with 150k structured annotations of social media posts, covering over 34k implications about a thousand demographic groups. We then establish baseline approaches that learn to recover SOCIAL BIAS FRAMES from unstructured text. We find that while stateof-the-art neural models are effective at highlevel categorization of whether a given statement projects unwanted social bias (80% F 1 ), they are not effective at spelling out more detailed explanations in terms of SOCIAL BIAS FRAMES. Our study motivates future work that combines structured pragmatic inference with commonsense reasoning on social implications. post off? int? lewd? group? targeted group implied statement ingroup? Kendrick just dropped the coldest video of all fucking time no no no What a fucking stupid bitch shut the fuck up already yes yes no need to fuck sum bad , I got some pressure built up :P no no yes I take a bitch home give her long dick yes yes yes no You annoyed me every day for months you're a fucking moron yes yes no no My problem with Korean artists: I dont know how to pronounce your name I can't hanggul to save my life yes no no yes Korean folks have weird names no I'll continue this thread till non-lifting fags stop lifting like idiots at the gym... Which is never. yes yes no yes gay men are weak and not manly no I thought drugs were the only things black people could shoot up Boy was I wrong yes yes no yes Black folks do drugs no kill people commit shootings
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 008ba994-ca03-407a-887a-928174c48df7Cited by top-tier papers106
- GLaM: Efficient Scaling of Language Models with Mixture-of-ExpertsNan Du, Yanping Huang, Andrew M. Dai, Simon Tong et al.ICML 2022 · 1,173 citations
- Towards Understanding and Mitigating Social Biases in Language ModelsPaul Pu Liang, Chiyu Wu, Louis-Philippe Morency, Ruslan SalakhutdinovICML 2021 · 495 citations
- Latent Hatred: A Benchmark for Understanding Implicit Hate SpeechMai ElSherief, Caleb Ziems, David Muchlinski, Vaishnavi Anupindi et al.EMNLP 2021 · 159 citations
- The Moral Integrity Corpus: A Benchmark for Ethical Dialogue SystemsCaleb Ziems, Jane A. Yu, Yi-Chia Wang, Alon Y. Halevy et al.ACL 2022 · 127 citations
- Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language ModelsMyra Cheng, Esin Durmus, Dan JurafskyACL 2023 · 89 citations
Builds on1
Related papers
- Multi-Dimensional Gender Bias ClassificationEmily Dinan, Angela Fan, Ledell Wu, Jason Weston et al.EMNLP 2020 · 7 citations
- Social-Group-Agnostic Bias Mitigation via the Stereotype Content ModelAli Omrani, Alireza Salkhordeh Ziabari, Charles Yu, Preni Golazizian et al.ACL 2023 · 13 citations
- Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?Anthony Dubreuil, Antoine Gourru, Christine Largeron, Amine TrabelsiEMNLP 2025 · 1 citation
- Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying PromptsYujie Lin, Kunquan Li, Yixuan Liao, Xiaoxin Chen et al.ICLR 2026 · 6 citations
- Social Story Frames: Contextual Reasoning about Narrative Intent and ReceptionJoel Mire, Maria Antoniak, Steven R. Wilson, Zexin Ma et al.ACL 2026 · 2 citations
