Challenge: toxicity detection models focus on marginalized groups, but they obscure harms faced by intersectional subgroups.
Approach: They use outlier detection to identify text about people with demographic attributes distant from the "norm" they find model performance is worse for demographic outliers than non-outliers .
Outcome: The proposed model performance is worse for outliers than non-outliers, the authors say . their analysis also shows that outlier analysis can identify harms faced by intersectional groups .

Similar Papers

Unveiling Identity Biases in Toxicity Detection : A Game-Focused Dataset and Reactivity Analysis Approach (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing datasets focused on gender or racial biases are not designed for the gaming industry, a concern for models built for toxicity detection in videogames’ written chat.
Approach: They propose to use reactivity analysis to highlight oversensitive terms using a language model developed by Ubisoft for toxicity detection on videogame’s written chat and Perspective API to generate a list of terms that trigger the models to varying degrees.
Outcome: The proposed model can detect and amplify identity biases in annotated language models and is compared with a language model developed by Ubisoft for toxicity detection on videogames’ written chat and Perspective API.
On the Role of Speech Data in Reducing Toxicity Detection Bias (2025.naacl-long)

Copied to clipboard

Challenge: Text toxicity detection systems produce disproportionate rates of false positives on demographic groups . toxicity classification systems often misinterpret benign group mentions as toxic .
Approach: They use group annotations to compare text-based and speech-based toxicity detection systems.
Outcome: The results show that access to speech data supports reduced bias against group mentions . the authors recommend improving classifiers, rather than transcription pipelines if possible .
Detoxifying Language Models Risks Marginalizing Minority Voices (2021.naacl-main)

Copied to clipboard

Challenge: Existing detoxification techniques have been proposed to mitigate toxic LM generations . e.g., detoxification makes LMs more brittle to distribution shift, especially on language used by marginalized groups .
Approach: They propose to use detoxification techniques to reduce toxic LM generations without affecting perplexity or generation quality on nontoxic inputs.
Outcome: The proposed methods hurt equity on language used by marginalized groups, the authors show . they show that detoxification makes LMs more brittle to distribution shift, they say .
ModelCitizens: Representing Community Voices in Online Safety (2025.emnlp-main)

Copied to clipboard

Challenge: Existing toxic language detection models are trained on annotations that collapse diverse perspectives into a single ground truth.
Approach: They propose to augment social media posts with conversational scenarios to reflect the impact of conversational context on toxicity.
Outcome: The proposed model outperforms existing models on social media with conversational scenarios.
Detecting Community Sensitive Norm Violations in Online Conversations (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing efforts to identify unacceptable behavior have focused on toxicity as the sole form of community norm violation.
Approach: They propose a dataset that focuses on a more complete spectrum of community norms and their violations in local conversational and global contexts.
Outcome: The proposed model improves the detection of community norm violations in local conversational and global contexts.
Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting (2020.acl-main)

Copied to clipboard

Challenge: Recent research has found that text classification datasets contain certain unintended biases, such as text containing demographic identity-terms that are more likely to be abusive.
Approach: They propose a model-agnostic debiasing framework that recovers the non-discrimination distribution using instance weighting, which does not require extra resources or annotations apart from a pre-defined set of demographic identity-terms.
Outcome: The proposed framework alleviates the unintended biases without hurting models’ generalization ability.
Challenges in Automated Debiasing for Toxic Language Detection (2021.eacl-main)

Copied to clipboard

Challenge: Existing methods for debiasing toxic language data are limited in their ability to prevent biased behavior in toxic language detection systems.
Approach: They propose to debiase toxic language detection models using lexical and dialectal markers using synthetic labels instead of traditional methods.
Outcome: The proposed method reduces dialectal associations with toxicity despite the use of synthetic labels .
ROBBIE: Robust Bias Evaluation of Large Generative Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: generative large language models (LLMs) are becoming more performant and prevalent . we need tools to measure and improve their fairness, authors say .
Approach: They propose to compare 6 different prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative large language models.
Outcome: The proposed model can be tested on more datasets to better characterize and mitigate biases . the study compared 6 prompt-based bias and toxicity metrics across 12 demographic axes and 5 families of generative large language models.
Social Bias Probing: Fairness Benchmarking for Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for evaluating social biases in language models have been limited to binary association tests on small datasets.
Approach: They propose a framework for probing language models for social biases by assessing disparate treatment . they use a large-scale benchmark to examine the diversity of identities and stereotypes .
Outcome: The proposed framework expands the analysis beyond the binary comparison of stereotypical versus anti-stereotypical identities to include a diverse range of identities and stereotypes.
LOGAN: Local Group Bias Detection by Clustering (2020.emnlp-main)

Copied to clipboard

Challenge: a number of machine learning models inherit and amplify the societal biases in data.
Approach: a new bias detection technique based on clustering is proposed to detect local biases in data . authors propose to use LOGAN to analyze local bias in data.
Outcome: The proposed technique detects bias in a local region and allows better analysis of model predictions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations