“Quantifying and Alleviating Political Bias in Language Models”, Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu, Soroush Vosoughi2022-03-01 (GPT-2, model-free RL, sociology of tech)⁠:

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 first describe metrics for measuring political bias in GPT-2 generation, and discuss several interesting takeaways:

1. The generation of vanilla GPT-2 model is mostly liberal-leaning,

2. Such political bias depends on the sensitive attributes mentioned in the context, and

3. Priming the generation with an explicit political identifier, the extent of political bias is imbalanced (between liberal and conservative).

We then propose a reinforcement learning (RL) framework for mitigating such 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 3 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.

[Keywords: bias in language models, natural language generation, political bias, measuring bias, mitigating bias]

See Also:

• “Reducing Non-Normative Text Generation from Language Models”

• “All the News That’s Fit to Fabricate: AI-Generated Text as a Tool of Media Misinformation”

• “Plug and Play Language Models: A Simple Approach to Controlled Text Generation”

• “Fine-Tuning GPT-2 from Human Preferences”

• “Language Models have a Moral Dimension”