arXiv AI July 20, 2026 By Indraveni Chebolu, Rohan Singh, Arnab Mallick, Harmesh Rana

Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 18

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

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.

By Zhouyuan Ma, Yutao Wu, Hanxun Huang, Xiang Zheng, Xiao Liu, Yixin Cao, Zuxuan Wu, Xingjun Ma, Yu-Gang Jiang

llms benchmarks safety

arXiv AI

Jul 28

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining

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.

By Rares A. C. Diaconescu, Iulia Slanina, Alina Florea, Andrei B. Trache, Miruna E. Coroi, Anne Arzberger, Jie Yang, Enrico Liscio

llms safety

arXiv AI

Aug 5

Obfuscation Rules for Detecting and Detoxifying Korean Toxicity

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.

By Yejin Lee, Su-Hyeon Kim, Hyundong Jin, Dayoung Kim, Yeonsoo Kim, Yo-Sub Han

llms safety

arXiv Machine Learning

Sep 22

Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs

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.

By Jiakun Li, Guowei Song, Sijia Li, Xingwei He, Hongzheng Chai, Yuan Yuan

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jul 24

thaulab@EEUCA 2026: Who Said What to Whom? A Targeting-Aware Neural-Symbolic Pipeline for Gaming Toxicity Detection

arXiv:2607. 20447v1 Announce Type: cross Abstract: This paper describes our system for the EEUCA 2026 Shared Task on toxicity classification in gaming chat.

By Anmol Guragain, Marcos Estecha-Garitagoitia, Luis Fernando D'Haro Enr\'iquez, Ricardo de C\'ordoba

llms safety

arXiv AI

Sep 1

Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines

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...

By Minkyu Kim, Juhwan Choi, YoungBin Kim

diffusion benchmarks safety

One email a morning, machine-written

Related stories

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining

Obfuscation Rules for Detecting and Detoxifying Korean Toxicity

Multilingual Safety Signals Are Multi-Layered: Filtering Safety-Degrading Data for Safer LLMs

thaulab@EEUCA 2026: Who Said What to Whom? A Targeting-Aware Neural-Symbolic Pipeline for Gaming Toxicity Detection

Not Safe for All: Auditing the Dialect Penalty in Text-to-Image Safety Pipelines