PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models

Published: 10 Jul 2024, Last Modified: 26 Aug 2024COLMEveryoneRevisionsBibTeXCC BY 4.0
Research Area: Data, Evaluation, Societal implications, Safety, LMs for everyone
Keywords: toxicity, evaluation, multilingual, large language models
TL;DR: We introduce PolygloToxicityPrompts, the first large-scale multilingual toxicity evaluation benchmark of 425K naturally-occurring prompts spanning 17 languages.
Abstract: Recent advances in large language models (LLMs) have led to their extensive global deployment, and ensuring their safety calls for comprehensive and multilingual toxicity evaluations. However, existing toxicity benchmarks are overwhelmingly focused on English, posing serious risks to deploying LLMs in other languages. We address this by introducing PolygloToxicityPrompts (PTP), the first large-scale multilingual toxicity evaluation benchmark of 425K naturally-occurring prompts spanning 17 languages. We overcome the scarcity of naturally occurring toxicity in web-text and ensure coverage across languages with varying resources by automatically scraping over 100M web-text documents. Using PTP, we investigate research questions to study the impact of model size, prompt language, and instruction and preference-tuning methods on toxicity by benchmarking over 60 LLMs. Notably, we find that toxicity increases as language resources decrease or model size increases. Although instruction- and preference-tuning reduce toxicity, the choice of preference-tuning method does not have any significant impact. Our findings shed light on crucial shortcomings of LLM safeguarding and highlight areas for future research.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html
Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html
Submission Number: 1165
Loading