mlsanityData to 7 Oct 2026

Mitigating Political Bias in Language Models Through Reinforced Calibration

arXiv 2104.14795 ↗First posted 30 Apr 2021cs.CL cs.AIcited by 73

Not on the map. Why?

Abstract (arXiv)

Current large-scale language models can be politically biased as a result of the data they are trained on, potentially causing serious problems when they are deployed in real-world settings. In this paper, we describe metrics for measuring political bias in GPT-2 generation and propose a reinforcement learning (RL) framework for mitigating political biases in generated text. By using rewards from word embeddings or a classifier, our RL framework guides debiased generation without having access to the training data or requiring the model to be retrained. In empirical experiments on three attributes sensitive to political bias (gender, location, and topic), our methods reduced bias according to both our metrics and human evaluation, while maintaining readability and semantic coherence.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 36 of its 56 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

36 of 56 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  6. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  7. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  8. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  9. 2018Model Cards for Model Reportingcited by 1,068
  10. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  11. 2017Counterfactual Fairnesscited by 802
  12. 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
24 more
  1. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 709
  2. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  3. 2018Gender Bias in Coreference Resolution: Evaluation and Debiasing Methodscited by 657
  4. 2019The Woman Worked as a Babysitter: On Biases in Language Generationcited by 540
  5. 2016Safe and Efficient Off-Policy Reinforcement Learningcited by 260
  6. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
  7. 2019Evaluating Gender Bias in Machine Translationcited by 247
  8. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  9. 2019Visualizing and Measuring the Geometry of BERTcited by 215
  10. 2019Identifying and Reducing Gender Bias in Word-Level Language Modelscited by 214
  11. 2018Learning Gender-Neutral Word Embeddingscited by 169
  12. 2018Reducing Gender Bias in Abusive Language Detectioncited by 152
  13. 2019Reducing Sentiment Bias in Language Models via Counterfactual Evaluationcited by 148
  14. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  15. 2019Wasserstein Fair Classificationcited by 131
  16. 2020Towards Controllable Biases in Language Generationcited by 112
  17. 2019It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitutioncited by 102
  18. 2020Few-shot Natural Language Generation for Task-Oriented Dialogcited by 89
  19. 2019Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representationcited by 84
  20. 2019Conditional Learning of Fair Representationscited by 78
  21. 2015Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labelscited by 64
  22. 2020Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generationcited by 47
  23. 2019Towards Making the Most of BERT in Neural Machine Translationcited by 43
  24. 2021Political Depolarization of News Articles Using Attribute-aware Word Embeddingscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 14; 2023: 18; 2024: 26; 2025: 7; 2026: 5.

73 papers.

Sort:

By area:

  1. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  2. 2024Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Modelscited by 467
  3. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 257
  4. 2022A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Modelscited by 128
  5. 2024Best Practices and Lessons Learned on Synthetic Datacited by 104
  6. 2022The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systemscited by 92
  7. 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
  8. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  9. 2023Training Socially Aligned Language Models on Simulated Social Interactionscited by 77
  10. 2024Bias in Large Language Models: Origin, Evaluation, and Mitigationcited by 77
  11. 2021On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmarkcited by 73
  12. 2023A Bibliometric Review of Large Language Models Research from 2017 to 2023cited by 56
38 more
  1. 2023TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Modelscited by 56
  2. 2023The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Valuescited by 53
  3. 2022POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detectioncited by 50
  4. 2022A Causal Lens for Controllable Text Generationcited by 45
  5. 2025FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steeringcited by 37
  6. 2024On the Relationship between Truth and Political Bias in Language Modelscited by 31
  7. 2024Stepwise Alignment for Constrained Language Model Policy Optimizationcited by 30
  8. 2024AI for social science and social science of AI: A Surveycited by 29
  9. 2024Navigating LLM Ethics: Advancements, Challenges, and Future Directionscited by 28
  10. 2022NeuS: Neutral Multi-News Summarization for Mitigating Framing Biascited by 26
  11. 2024Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Surveycited by 23
  12. 2022Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Surveycited by 22
  13. 2022Longitudinal Fairness with Censorshipcited by 21
  14. 2022Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisementscited by 21
  15. 2021Assessing Political Prudence of Open-domain Chatbotscited by 20
  16. 2023SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructionscited by 19
  17. 2024Can AI Be as Creative as Humans?cited by 17
  18. 2024GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancycited by 14
  19. 2024ControlCap: Controllable Region-level Captioningcited by 13
  20. 2023She Elicits Requirements and He Tests: Software Engineering Gender Bias in Large Language Modelscited by 12
  21. 2023Can Language Model Moderators Improve the Health of Online Discourse?cited by 12
  22. 2024Will the Real Linda Please Stand up...to Large Language Models? Examining the Representativeness Heuristic in LLMscited by 12
  23. 2024Montessori-Instruct: Generate Influential Training Data Tailored for Student Learningcited by 12
  24. 2022Non-Parallel Text Style Transfer with Self-Parallel Supervisioncited by 11
  25. 2023Tackling Bias in Pre-trained Language Models: Current Trends and Under-represented Societiescited by 11
  26. 2023The Media Bias Taxonomy: A Systematic Literature Review on the Forms and Automated Detection of Media Biascited by 11
  27. 2024Persona Setting Pitfall: Persistent Outgroup Biases in Large Language Models Arising from Social Identity Adoptioncited by 9
  28. 2022Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Biascited by 8
  29. 2022HERB: Measuring Hierarchical Regional Bias in Pre-trained Language Modelscited by 8
  30. 2024LLMAuditor: A Framework for Auditing Large Language Models Using Human-in-the-Loopcited by 8
  31. 2021Language Model Augmented Relevance Scorecited by 7
  32. 2022An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generationcited by 7
  33. 2024When Neutral Summaries are not that Neutral: Quantifying Political Neutrality in LLM-Generated News Summariescited by 7
  34. 2026Uncovering Political Bias in Large Language Models using Parliamentary Voting Recordscited by 7
  35. 2022EnDex: Evaluation of Dialogue Engagingness at Scalecited by 6
  36. 2023FairPy: A Toolkit for Evaluation of Prediction Biases and their Mitigation in Large Language Modelscited by 5
  37. 2024I Am Not Them: Fluid Identities and Persistent Out-group Bias in Large Language Modelscited by 5
  38. 2025Framing Political Bias in Multilingual LLMs Across Pakistani Languagescited by 5

50 most cited of 73 All 73 (JSON)