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

• URL: http://arxiv.org/abs/2607.15861v1
• Date: Fri, 17 Jul 2026 11:21:29 GMT
• Title: Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection
• Abstract summary: We study the emphconditional reliability of toxicity priors in Indian multilingual and code-mixed short text.<n>We propose ToxGate, a trust-fusion head that conditions each auxiliary signal on the encoder representation before adding it to the prediction state.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch. We study the \emph{conditional reliability} of toxicity priors in Indian multilingual and code-mixed short text: English toxicity, Indic abuse, and rule-based severity cues can be useful evidence, but only in some linguistic and abuse-severity contexts. We propose ToxGate, a trust-fusion head that conditions each auxiliary signal on the encoder representation before adding it to the prediction state. Across three short-text abuse datasets, four transformer encoders, and five seeds per setting, ToxGate improves over matched plain encoders in 10 of 12 in-domain settings and 7 of 8 transfer settings. The largest and most interpretable gains occur in high-risk moderation slices, including explicit slurs, violent threats, and cross-dataset transfer. The broader lesson is that moderation systems should treat external toxicity tools and priors as conditional evidence rather than fixed features or ground truth, in focused ablations, source-specific gating gives the strongest results in transfer, severe-abuse slices, and high-risk triage.

Related papers

• Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues [17.62673716826934]
  We present ToxiAlert-Bench, a large-scale audio dataset annotated with seven major toxic categories and twenty fine-grained toxic labels.<n>We propose a dual-head neural network with a multi-stage training strategy tailored for toxic speech detection.<n>Our experimental results show that leveraging paralinguistic features significantly improves detection performance.
  arXiv  Detail & Related papers  (2026-05-15T14:17:19Z)
• MUTEX: Leveraging Multilingual Transformers and Conditional Random Fields for Enhanced Urdu Toxic Span Detection [0.41292255339309664]
  MUTEX is a multilingual transformer combined with conditional random fields (CRF) for Urdu toxic span detection framework.<n> MUTEX achieves 60% token-level F1 score that is the first supervised baseline for Urdu toxic span detection.
  arXiv  Detail & Related papers  (2026-03-05T11:11:50Z)
• Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework [58.01529356381494]
  We propose a novel detection framework based on Toxicity Association Graphs (TAGs)<n>We introduce the first quantifiable metric for hidden toxicity, the Multimodal Toxicity Covertness (MTC)<n>Our approach enables precise identification of covert toxicity while preserving full interpretability of the decision-making process.
  arXiv  Detail & Related papers  (2026-02-03T08:54:25Z)
• Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective [104.09817371557476]
  Large language models (LLMs) have achieved impressive results across a range of natural language processing tasks.<n>Their potential to generate harmful content has raised serious safety concerns.<n>We introduce three novel multi-label benchmarks for toxicity detection.
  arXiv  Detail & Related papers  (2025-10-16T06:50:33Z)
• SynCED-EnDe 2025: A Synthetic and Curated English - German Dataset for Critical Error Detection in Machine Translation [1.4517170578045737]
  Critical Error Detection in machine translation aims to determine whether a translation is safe to use or contains unacceptable deviations in meaning.<n>We present SynCED-EnDe, a new resource consisting of 1,000 gold-labeled and 8,000 silver-labeled sentence pairs.<n>We envision SynCED-EnDe as a community resource to advance safe deployment of MT in information retrieval and conversational assistants.
  arXiv  Detail & Related papers  (2025-10-01T22:38:56Z)
• Toxicity-Aware Few-Shot Prompting for Low-Resource Singlish Translation [3.7678366606419345]
  Translating toxic content between low-resource language pairs poses challenges due to scarce parallel data and safety filters that sanitize offensive expressions.<n>We propose a two-stage framework for toxicity-preserving translation, demonstrated on a code-mixed Singlish safety corpus.<n>By positioning Singlish as a testbed for inclusive NLP, we underscore the importance of preserving sociolinguistic nuance in real-world applications.
  arXiv  Detail & Related papers  (2025-07-16T06:58:02Z)
• CRAT: A Multi-Agent Framework for Causality-Enhanced Reflective and Retrieval-Augmented Translation with Large Language Models [59.8529196670565]
  CRAT is a novel multi-agent translation framework that leverages RAG and causality-enhanced self-reflection to address translation challenges. Our results show that CRAT significantly improves translation accuracy, particularly in handling context-sensitive terms and emerging vocabulary.
  arXiv  Detail & Related papers  (2024-10-28T14:29:11Z)
• Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models [26.474136481185724]
  Fine-grained detoxification via instance-level prefixes (FGDILP) to mitigate toxic text without additional cost. FGDILP contrasts the contextualized representation in attention space using a positive prefix-prepended prompt. We validate that FGDILP enables controlled text generation with regard to toxicity at both the utterance and context levels.
  arXiv  Detail & Related papers  (2024-02-23T09:04:48Z)
• Toxicity in Multilingual Machine Translation at Scale [3.4620477930009472]
  We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages. An automatic toxicity evaluation shows that added toxicity across languages varies from 0% to 5%. The output languages with the most added toxicity tend to be low-resource ones, and the demographic axes with the most added toxicity include sexual orientation, gender and sex, and ability.
  arXiv  Detail & Related papers  (2022-10-06T17:26:27Z)
• Toxicity Detection can be Sensitive to the Conversational Context [64.28043776806213]
  We construct and publicly release a dataset of 10,000 posts with two kinds of toxicity labels. We introduce a new task, context sensitivity estimation, which aims to identify posts whose perceived toxicity changes if the context is also considered.
  arXiv  Detail & Related papers  (2021-11-19T13:57:26Z)
• Challenges in Automated Debiasing for Toxic Language Detection [81.04406231100323]
  Biased associations have been a challenge in the development of classifiers for detecting toxic language. We investigate recently introduced debiasing methods for text classification datasets and models, as applied to toxic language detection. Our focus is on lexical (e.g., swear words, slurs, identity mentions) and dialectal markers (specifically African American English)
  arXiv  Detail & Related papers  (2021-01-29T22:03:17Z)
• RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models [93.151822563361]
  Pretrained neural language models (LMs) are prone to generating racist, sexist, or otherwise toxic language which hinders their safe deployment. We investigate the extent to which pretrained LMs can be prompted to generate toxic language, and the effectiveness of controllable text generation algorithms at preventing such toxic degeneration.
  arXiv  Detail & Related papers  (2020-09-24T03:17:19Z)

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.