# Mitigating Political Bias in Language Models Through Reinforced Calibration

arXiv: https://arxiv.org/abs/2104.14795 · HTML: https://mlsanity.com/paper/2104.14795/

## Key facts

- Cited by 73 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 56 references that are in the map.
- First posted on arXiv 30 Apr 2021.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Model Cards for Model Reporting](https://mlsanity.com/paper/1810.03993/) (2018)
- [DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation](https://mlsanity.com/paper/1911.00536/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Safe and Efficient Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1606.02647/) (2016)
- [Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes](https://mlsanity.com/paper/1711.08412/) (2017)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Empirical Risk Minimization under Fairness Constraints](https://mlsanity.com/paper/1802.08626/) (2018)
- [Visualizing and Measuring the Geometry of BERT](https://mlsanity.com/paper/1906.02715/) (2019)
- [Identifying and Reducing Gender Bias in Word-Level Language Models](https://mlsanity.com/paper/1904.03035/) (2019)
- [Learning Gender-Neutral Word Embeddings](https://mlsanity.com/paper/1809.01496/) (2018)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [Reducing Sentiment Bias in Language Models via Counterfactual Evaluation](https://mlsanity.com/paper/1911.03064/) (2019)
- [Inherent Tradeoffs in Learning Fair Representations](https://mlsanity.com/paper/1906.08386/) (2019)
- [Wasserstein Fair Classification](https://mlsanity.com/paper/1907.12059/) (2019)
- [Towards Controllable Biases in Language Generation](https://mlsanity.com/paper/2005.00268/) (2020)
- [It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution](https://mlsanity.com/paper/1909.00871/) (2019)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)

## Built on by (most cited first, 30 of 73)

- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Best Practices and Lessons Learned on Synthetic Data](https://mlsanity.com/paper/2404.07503/) (2024)
- [The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems](https://mlsanity.com/paper/2204.03021/) (2022)
- [Measuring Political Bias in Large Language Models: What Is Said and How It Is Said](https://mlsanity.com/paper/2403.18932/) (2024)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Training Socially Aligned Language Models on Simulated Social Interactions](https://mlsanity.com/paper/2305.16960/) (2023)
- [Bias in Large Language Models: Origin, Evaluation, and Mitigation](https://mlsanity.com/paper/2411.10915/) (2024)
- [On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark](https://mlsanity.com/paper/2110.08466/) (2021)
- [TrustGPT: A Benchmark for Trustworthy and Responsible Large Language Models](https://mlsanity.com/paper/2306.11507/) (2023)
- [A Bibliometric Review of Large Language Models Research from 2017 to 2023](https://mlsanity.com/paper/2304.02020/) (2023)
- [The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values](https://mlsanity.com/paper/2310.07629/) (2023)
- [POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection](https://mlsanity.com/paper/2205.00619/) (2022)
- [A Causal Lens for Controllable Text Generation](https://mlsanity.com/paper/2201.09119/) (2022)
- [FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering](https://mlsanity.com/paper/2504.14492/) (2025)
- [On the Relationship between Truth and Political Bias in Language Models](https://mlsanity.com/paper/2409.05283/) (2024)
- [Stepwise Alignment for Constrained Language Model Policy Optimization](https://mlsanity.com/paper/2404.11049/) (2024)
- [AI for social science and social science of AI: A Survey](https://mlsanity.com/paper/2401.11839/) (2024)
- [Navigating LLM Ethics: Advancements, Challenges, and Future Directions](https://mlsanity.com/paper/2406.18841/) (2024)
- [NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias](https://mlsanity.com/paper/2204.04902/) (2022)
- [Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey](https://mlsanity.com/paper/2406.05392/) (2024)
- [Longitudinal Fairness with Censorship](https://mlsanity.com/paper/2203.16024/) (2022)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Looking for a Handsome Carpenter! Debiasing GPT-3 Job Advertisements](https://mlsanity.com/paper/2205.11374/) (2022)
- [Assessing Political Prudence of Open-domain Chatbots](https://mlsanity.com/paper/2106.06157/) (2021)
- [SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions](https://mlsanity.com/paper/2307.01139/) (2023)
- [Can AI Be as Creative as Humans?](https://mlsanity.com/paper/2401.01623/) (2024)
- [GermanPartiesQA: Benchmarking Commercial Large Language Models and AI Companions for Political Alignment and Sycophancy](https://mlsanity.com/paper/2407.18008/) (2024)

## 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.