machine-generated text

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 (Brown et al., 2020). 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.

Since the remarkable generation performance of large language models raised ethical and legal concerns, approaches to detect machine-generated text by embedding watermarks are being developed. However, we discover that the existing works fail to function appropriately in code generation tasks due to the task’s nature of having low entropy. Extending a logit-modifying watermark method, we propose Selective WatErmarking via Entropy Thresholding (SWEET), which enhances detection ability and mitigates code quality degeneration by removing low-entropy segments at generating and detecting watermarks. Our experiments show that SWEET significantly improves code quality preservation while outperforming all baselines, including post-hoc detection methods, in detecting machine-generated code text. Our code is available in https://github.com/hongcheki/sweet-watermark.

LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment. In this work we dispute this claim, identifying watermark stealing (WS) as a fundamental vulnerability of these schemes. We show that querying the API of the watermarked LLM to approximately reverse-engineer a watermark enables practical spoofing attacks, as hypothesized in prior work, but also greatly boosts scrubbing attacks, which was previously unnoticed. We are the first to propose an automated WS algorithm and use it in the first comprehensive study of spoofing and scrubbing in realistic settings. We show that for under $50 an attacker can both spoof and scrub state-of-the-art schemes previously considered safe, with average success rate of over 80%. Our findings challenge common beliefs about LLM watermarking, stressing the need for more robust schemes. We make all our code and additional examples available at https://watermark-stealing.org.