mlsanityData to 14 Oct 2026

Social Bias Frames: Reasoning about Social and Power Implications of Language

arXiv 1911.03891 ↗First posted 10 Nov 2019cs.CLcited by 380

Not on the map. Why?

Abstract (arXiv)

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 state-of-the-art neural models are effective at high-level categorization of whether a given statement projects unwanted social bias (80% F1), 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.

Key facts. Cited by 380 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 51; 2023: 99; 2024: 74; 2025: 62; 2026: 56.

380 papers.

Sort:

By area:

  1. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  2. 2023PaLM 2 Technical Reportcited by 1,162
  3. 2021GLaM: Efficient Scaling of Language Models with Mixture-of-Expertscited by 897
  4. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 729
  5. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  6. 2021DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Expertscited by 441
  7. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  8. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 422
  9. 2021Towards Understanding and Mitigating Social Biases in Language Modelscited by 296
  10. 2021Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detectioncited by 264
  11. 2023Can Large Language Models Transform Computational Social Science?cited by 250
  12. 2023Large Language Model Alignment: A Surveycited by 243
38 more
  1. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 217
  2. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 207
  3. 2023Gender bias and stereotypes in Large Language Modelscited by 187
  4. 2023A Pretrainer's Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicitycited by 182
  5. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 173
  6. 2021Challenges in Detoxifying Language Modelscited by 169
  7. 2024Quantifying the Persona Effect in LLM Simulationscited by 169
  8. 2023Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speechcited by 166
  9. 2022Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?cited by 155
  10. 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 149
  11. 2021Can Machines Learn Morality? The Delphi Experimentcited by 141
  12. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  13. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 123
  14. 2021Gender Bias in Machine Translationcited by 117
  15. 2022ProsocialDialog: A Prosocial Backbone for Conversational Agentscited by 109
  16. 2021Detoxifying Language Models Risks Marginalizing Minority Voicescited by 107
  17. 2023Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Dutiescited by 97
  18. 2021Challenges in Automated Debiasing for Toxic Language Detectioncited by 96
  19. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 93
  20. 2022When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgmentcited by 93
  21. 2023When the Majority is Wrong: Modeling Annotator Disagreement for Subjective Taskscited by 90
  22. 2021Few-Shot Self-Rationalization with Natural Language Promptscited by 83
  23. 2021Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speechcited by 82
  24. 2021On Measures of Biases and Harms in NLPcited by 81
  25. 2024Safeguarding Large Language Models: A Surveycited by 78
  26. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  27. 2022COLD: A Benchmark for Chinese Offensive Language Detectioncited by 76
  28. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 75
  29. 2022On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representationscited by 75
  30. 2021Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreementcited by 72
  31. 2022CREPE: Open-Domain Question Answering with False Presuppositionscited by 72
  32. 2021Towards generalisable hate speech detection: a review on obstacles and solutionscited by 66
  33. 2023Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmarkcited by 63
  34. 2024Massively Multi-Cultural Knowledge Acquisition & LM Benchmarkingcited by 63
  35. 2022Theories of "Gender" in NLP Bias Researchcited by 62
  36. 2023Natural Language Reasoning, A Surveycited by 61
  37. 2023NormBank: A Knowledge Bank of Situational Social Normscited by 60
  38. 2025PolyGuard: A Multilingual Safety Moderation Tool for 17 Languagescited by 59

50 most cited of 380 All 380 (JSON)