Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection
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 data
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Indraveni Chebolu →
“Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection”
- LinkedLinked via arxiv author · 85%Rohan Singh →
“Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection”
- LinkedLinked via arxiv author · 85%Arnab Mallick →
“Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection”
- LinkedLinked via arxiv author · 85%Harmesh Rana →
“Conditional Reliability of Toxicity Signals for Multilingual and Code-Mixed Abuse Detection”