Saved in:
Bibliographic Details
Main Authors: Jain, Devansh, Kumar, Priyanshu, Gehman, Samuel, Zhou, Xuhui, Hartvigsen, Thomas, Sap, Maarten
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.09373
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910562463514624
author Jain, Devansh
Kumar, Priyanshu
Gehman, Samuel
Zhou, Xuhui
Hartvigsen, Thomas
Sap, Maarten
author_facet Jain, Devansh
Kumar, Priyanshu
Gehman, Samuel
Zhou, Xuhui
Hartvigsen, Thomas
Sap, Maarten
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09373
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
Jain, Devansh
Kumar, Priyanshu
Gehman, Samuel
Zhou, Xuhui
Hartvigsen, Thomas
Sap, Maarten
Computation and Language
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.
title PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models
topic Computation and Language
url https://arxiv.org/abs/2405.09373