Benchmarks › Toxigen

Toxigen

Benchmark indicates whether a system detects implicit hate speech targeting minority groups while avoiding false alarms

Full title

ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

Tag

toxigen (use this to limit an assistant's search to this benchmark)

Reference

arxiv.org/abs/2203.09509

Related links

github.com/microsoft/ToxiGen

BenchRisk

Scored 2025-04-01 · 48 mitigations adopted, 138 absent · score page · source entry

Documents available to assistants

Summary from the reference

Toxic language detection systems often falsely flag text that contains minority group mentions as toxic, as those groups are often the targets of online hate. Such over-reliance on spurious correlations also causes systems to struggle with detecting implicitly toxic language. To help mitigate these issues, we create ToxiGen, a new large-scale and machine-generated dataset of 274k toxic and benign statements about 13 minority groups. We develop a demonstration-based prompting framework and an adversarial classifier-in-the-loop decoding method to generate subtly toxic and benign text with a massive pretrained language model. Controlling machine generation in this way allows ToxiGen to cover implicitly toxic text at a larger scale, and about more demographic groups, than previous resources of human-written text. We conduct a human evaluation on a challenging subset of ToxiGen and find that annotators struggle to distinguish machine-generated text from human-written language. We also find that 94.5% of toxic examples are labeled as hate speech by human annotators. Using three publicly-available datasets, we show that finetuning a toxicity classifier on our data improves its performance on human-written data substantially. We also demonstrate that ToxiGen can be used to fight machine-generated toxicity as finetuning improves the classifier significantly on our evaluation subset. Our code and data can be found at [this https URL.](https://github.com/microsoft/ToxiGen)

Ask an assistant about it

Once your assistant is connected, try a question such as “Using the benchmark sources, how is Toxigen scored?”

Developers can restrict a search to this benchmark with the filter {"benchmark": "toxigen"} on the MCP endpoint https://ns-f1fc49e3-9bca-4aa2-b5a1-ef5dbc18588f.search.ai.cloudflare.com/mcp.