conftrace_

toxicity classification

14 papers

Explore in graph

Co-occurring keywords

bias mitigation (500) text classification (6793) hate speech detection (723) transformer model (1996) large language model (13587) data augmentation (3052) natural language processing (2034) soft-label weight (1) group distributionally robust optimization (6) out-of-distribution risk (1)

Papers

DeepPavlov Strikes Back: A Toolkit for Improving LLM Reliability and Trustworthiness EACL 2026
ToxiGAN: Toxic Data Augmentation via LLM-Guided Directional Adversarial Generation EACL 2026
A Disaggregated Dataset on English Offensiveness Containing Spans EMNLP 2025
Learning Subjective Label Distributions via Sociocultural Descriptors EMNLP 2025
Debiasing by obfuscating with 007-classifiers promotes fairness in multi-community settings COLING 2025
Cross-lingual Text Classification Transfer: The Case of Ukrainian COLING 2025
Soft-Label Integration for Robust Toxicity Classification NIPS 2024
Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment INTERSPEECH 2024
Improving Covert Toxicity Detection by Retrieving and Generating References NAACL 2024
Detecting Unintended Social Bias in Toxic Language Datasets EMNLP 2022
Don’t Just Clean It, Proxy Clean It: Mitigating Bias by Proxy in Pre-Trained Models EMNLP 2022
Detecting Unintended Social Bias in Toxic Language Datasets CONLL 2022
Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company’s Reputation EACL 2021
LOGAN: Local Group Bias Detection by Clustering EMNLP 2020