Causal ATE Mitigates Unintended Bias in Controlled Text Generation
This addresses unintended bias towards protected groups in language models after detoxification, which is an incremental improvement over existing methods.
The paper tackles the problem of unintended bias in controlled text generation, particularly in toxicity mitigation, by using Causal Average Treatment Effect (Causal ATE) to remove spurious correlations that cause models to hallucinate attributes, showing it effectively solves this bias.
We study attribute control in language models through the method of Causal Average Treatment Effect (Causal ATE). Existing methods for the attribute control task in Language Models (LMs) check for the co-occurrence of words in a sentence with the attribute of interest, and control for them. However, spurious correlation of the words with the attribute in the training dataset, can cause models to hallucinate the presence of the attribute when presented with the spurious correlate during inference. We show that the simple perturbation-based method of Causal ATE removes this unintended effect. Specifically, we ground it in the problem of toxicity mitigation, where a significant challenge lies in the inadvertent bias that often emerges towards protected groups post detoxification. We show that this unintended bias can be solved by the use of the Causal ATE metric and rigorously prove our claim. We provide experimental validations for our claims and release our code (anonymously) here: https://github.com/causalate-mitigates-bias/causal-ate-mitigates-bias.