arXiv:2607. 15861v1 Announce Type: cross Abstract: Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch.
arXiv:2608. 14577v1 Announce Type: cross Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis.
arXiv:2607. 23175v1 Announce Type: cross Abstract: Reducing toxicity is often framed as a global alignment problem, yet perceptions of harmful language are subjective and context-dependent.
arXiv:2510. 10961v4 Announce Type: replace-cross Abstract: As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention.
The paper introduces MMSAFE, a multi-layer framework designed to identify safety-degrading data in multilingual large language models. It shows that safety signals are distributed across multiple layers and only partially shared across languages, unlike the single-layer assumption used in monolingual settings. Experiments demonstrate that MMSAFE reduces harmful-response rates by 60% compared to random filtering and outperforms the best single-layer baseline across various models, languages, and safety benchmarks.
arXiv:2607. 20447v1 Announce Type: cross Abstract: This paper describes our system for the EEUCA 2026 Shared Task on toxicity classification in gaming chat.
arXiv:2608.29589v1 Announce Type: new Abstract: Text-to-image (T2I) safety guardrails fail to generalize equitably to non-standard dialects. Evaluating 23,080 paired prompts across five English diale...
The paper introduces BanglaSafe, a benchmark of 879 Bengali prompts that covers 17 culturally grounded harm categories and five prompting conditions. Evaluation of 18 frontier LLMs shows that 53.6% of responses are unsafe or partially unsafe, with 14.7% containing strictly harmful content. The study finds that the writing style within Bengali has a stronger impact on safety than the language switch itself, and that current safety classifiers struggle to reliably evaluate Bengali content.
IndicSafeEval is a new evaluation framework that tests the safety robustness of large language models against persuasion-based jailbreak attacks in Indian languages. The benchmark covers ten safety-critical content categories, six persuasive strategies, and four languages—Hindi, Bengali, Marathi, and Punjabi—producing 7,200 adversarial prompts. Experiments show that model safety varies significantly across languages, prompt styles, and risk categories, highlighting gaps in current English-centric safety assessments.
IndicSafeEval is a new evaluation framework that tests the safety robustness of large language models against persuasion-based jailbreak attacks in Indian languages. The benchmark includes 7,200 adversarial prompts covering ten safety-critical content categories, six persuasive strategies, and four languages (Hindi, Bengali, Marathi, Punjabi). Experiments show that model safety varies significantly across languages, prompt styles, and risk categories, revealing that current English-centric safety evaluations miss important multilingual vulnerabilities.
arXiv:2606. 07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge.
arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.
arXiv:2605.28013v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vi...