Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI
This work addresses the challenge of toxicity detection for internet content moderation, highlighting pitfalls in widely used tools to prevent disparate harms, though it is incremental as it focuses on benchmarking rather than proposing a new method.
The paper tackled the problem of detecting toxic language by evaluating the PERSPECTIVE tool on a new benchmark called SASS, revealing significant shortcomings in its performance across various toxicity categories compared to low-effort alternatives like GPT-3 prompts.
Detecting "toxic" language in internet content is a pressing social and technical challenge. In this work, we focus on PERSPECTIVE from Jigsaw, a state-of-the-art tool that promises to score the "toxicity" of text, with a recent model update that claims impressive results (Lees et al., 2022). We seek to challenge certain normative claims about toxic language by proposing a new benchmark, Selected Adversarial SemanticS, or SASS. We evaluate PERSPECTIVE on SASS, and compare to low-effort alternatives, like zero-shot and few-shot GPT-3 prompt models, in binary classification settings. We find that PERSPECTIVE exhibits troubling shortcomings across a number of our toxicity categories. SASS provides a new tool for evaluating performance on previously undetected toxic language that avoids common normative pitfalls. Our work leads us to emphasize the importance of questioning assumptions made by tools already in deployment for toxicity detection in order to anticipate and prevent disparate harms.