Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts
This work addresses bias evaluation for NLG systems, but it is incremental as it builds on existing methods by improving prompt diversity.
The paper tackles the problem of unreliable bias evaluation in natural language generation systems by introducing syntactically-diverse prompts, showing that some structures lead to contradictory conclusions and more toxic content, while others reduce bias.
We present a robust methodology for evaluating biases in natural language generation(NLG) systems. Previous works use fixed hand-crafted prefix templates with mentions of various demographic groups to prompt models to generate continuations for bias analysis. These fixed prefix templates could themselves be specific in terms of styles or linguistic structures, which may lead to unreliable fairness conclusions that are not representative of the general trends from tone varying prompts. To study this problem, we paraphrase the prompts with different syntactic structures and use these to evaluate demographic bias in NLG systems. Our results suggest similar overall bias trends but some syntactic structures lead to contradictory conclusions compared to past works. We show that our methodology is more robust and that some syntactic structures prompt more toxic content while others could prompt less biased generation. This suggests the importance of not relying on a fixed syntactic structure and using tone-invariant prompts. Introducing syntactically-diverse prompts can achieve more robust NLG (bias) evaluation.