Mitigating Political Bias in Language Models through Reinforced Calibration

No. 17: IAAI-21, EAAI-21, AAAI-21 Special Programs and Special Track

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 35

AAAI Special Track on AI for Social Impact

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.

10.1609/aaai.v35i17.17744