A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models

• URL: http://arxiv.org/abs/2606.25380v1
• Date: Wed, 24 Jun 2026 04:24:30 GMT
• Title: A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models
• Abstract summary: This survey synthesizes work on toxicity detection and detoxification for multilingual language models.<n>We first catalogue threat models that exploit language choice, translation pivots, code-switching, orthographic variation, multi-turn interaction, and post-deployment fine-tuning to weaken safety alignment.<n>We then organize task formulations (toxic-to-neutral rewriting, toxicity classification, and toxic-generation evaluation), multilingual detection approaches, and mitigation strategies.
• Score: 21.145305563840697
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) are increasingly deployed across languages, but their safety behavior remains uneven across linguistic and cultural contexts. This survey synthesizes work on toxicity detection and detoxification for multilingual LLMs. We first catalogue threat models that exploit language choice, translation pivots, code-switching, orthographic variation, multi-turn interaction, and post-deployment fine-tuning to weaken safety alignment. We then organize task formulations (toxic-to-neutral rewriting, toxicity classification, and toxic-generation evaluation), multilingual detection approaches (cross-lingual encoders, translation pipelines, representation-level probes, and LLM-based detectors), and mitigation strategies spanning data filtering, supervised and preference-based tuning, decoding-time steering, representation editing, and multilingual guardrails. Across these areas, we identify persistent challenges: uneven language coverage, culturally contingent definitions of harm, fragmented evaluation protocols, and the risk that detoxification suppresses legitimate dialectal or identity-related expression.

Related papers

• DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection [68.92080038934164]
  This study introduces DetectRL-X, a benchmark designed to evaluate advanced detectors across 8 dimensions.<n>The benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to misuse.
  arXiv  Detail & Related papers  (2026-05-15T01:29:26Z)
• Multilingual Refusal Alignment for Safer Large Language Models [53.64286756804503]
  We investigate whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities.<n>We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models.<n>Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.
  arXiv  Detail & Related papers  (2026-04-24T09:29:14Z)
• Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification [7.696781721646013]
  We investigate false refusal behavior in hate speech detoxification.<n>We show that large language models (LLMs) disproportionately refuse inputs with higher semantic toxicity.<n>We propose a simple cross-translation strategy, translating English hate speech into Chinese for detoxification and back.
  arXiv  Detail & Related papers  (2026-01-13T15:45:31Z)
• Refusal Direction is Universal Across Safety-Aligned Languages [66.64709923081745]
  In this paper, we investigate the refusal behavior in large language models (LLMs) across 14 languages using PolyRefuse.<n>We uncover the surprising cross-lingual universality of the refusal direction: a vector extracted from English can bypass refusals in other languages with near-perfect effectiveness.<n>We attribute this transferability to the parallelism of refusal vectors across languages in the embedding space and identify the underlying mechanism behind cross-lingual jailbreaks.
  arXiv  Detail & Related papers  (2025-05-22T21:54:46Z)
• Breaking mBad! Supervised Fine-tuning for Cross-Lingual Detoxification [39.711527571739666]
  "Cross-lingual Detoxification" is a paradigm that mitigates toxicity in large language models.<n>We analyze toxicity reduction in cross-distribution settings and investigate how mitigation impacts model performance on non-toxic tasks.
  arXiv  Detail & Related papers  (2025-05-22T14:30:14Z)
• Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Models [56.61984030508691]
  We present the first mechanistic interpretability study of language confusion.<n>We show that confusion points (CPs) are central to this phenomenon.<n>We show that editing a small set of critical neurons, identified via comparative analysis with a multilingual-tuned counterpart, substantially mitigates confusion.
  arXiv  Detail & Related papers  (2025-05-22T11:29:17Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.77103365251923]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• Benchmarking LLM Guardrails in Handling Multilingual Toxicity [57.296161186129545]
  We introduce a comprehensive multilingual test suite, spanning seven datasets and over ten languages, to benchmark the performance of state-of-the-art guardrails. We investigate the resilience of guardrails against recent jailbreaking techniques, and assess the impact of in-context safety policies and language resource availability on guardrails' performance. Our findings show that existing guardrails are still ineffective at handling multilingual toxicity and lack robustness against jailbreaking prompts.
  arXiv  Detail & Related papers  (2024-10-29T15:51:24Z)
• PolygloToxicityPrompts: Multilingual Evaluation of Neural Toxic Degeneration in Large Language Models [27.996123856250065]
  Existing toxicity benchmarks are overwhelmingly focused on English. We introduce PolygloToxicityPrompts (PTP), the first large-scale multilingual toxicity evaluation benchmark of 425K naturally occurring prompts spanning 17 languages.
  arXiv  Detail & Related papers  (2024-05-15T14:22:33Z)
• From One to Many: Expanding the Scope of Toxicity Mitigation in Language Models [10.807067327137855]
  As language models embrace multilingual capabilities, it's crucial our safety measures keep pace. In the absence of sufficient annotated datasets across languages, we employ translated data to evaluate and enhance our mitigation techniques. This allows us to examine the effects of translation quality and the cross-lingual transfer on toxicity mitigation.
  arXiv  Detail & Related papers  (2024-03-06T17:51:43Z)
• Vicinal Risk Minimization for Few-Shot Cross-lingual Transfer in Abusive Language Detection [19.399281609371258]
  Cross-lingual transfer learning from high-resource to medium and low-resource languages has shown encouraging results. We resort to data augmentation and continual pre-training for domain adaptation to improve cross-lingual abusive language detection.
  arXiv  Detail & Related papers  (2023-11-03T16:51:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.