SOTAVerified|Agents Browse Leaderboard About

Bias Detection

Bias detection is the task of detecting and measuring racism, sexism and otherwise discriminatory behavior in a model (Source: https://stereoset.mit.edu/)

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 111–120 of 199 papers

Title	Date	Tasks	Status	Hype
Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis	Sep 30, 2023	Bias DetectionDecision Making	—Unverified	0
Investigating Subtler Biases in LLMs: Ageism, Beauty, Institutional, and Nationality Bias in Generative Models	Sep 16, 2023	Age/Bias-conflictingBias Detection	CodeCode Available	0
Unsupervised Bias Detection in College Student Newspapers	Sep 11, 2023	Bias DetectionLanguage Modeling	—Unverified	0
LUCID-GAN: Conditional Generative Models to Locate Unfairness	Jul 28, 2023	Bias DetectionFairness	CodeCode Available	0
Auditing Predictive Models for Intersectional Biases	Jun 22, 2023	Bias DetectionFairness	—Unverified	0
Trade-Offs Between Fairness and Privacy in Language Modeling	May 24, 2023	Bias DetectionFairness	CodeCode Available	0
Language-Agnostic Bias Detection in Language Models with Bias Probing	May 22, 2023	Bias Detection	CodeCode Available	0
Bipol: A Novel Multi-Axes Bias Evaluation Metric with Explainability for NLP	Apr 8, 2023	Bias DetectionSentence	CodeCode Available	0
Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy	Apr 5, 2023	ArticlesBias Detection	CodeCode Available	0
Adding Instructions during Pretraining: Effective Way of Controlling Toxicity in Language Models	Feb 14, 2023	Bias DetectionData Augmentation	—Unverified	0

Show:10 25 50

← PrevPage 12 of 20Next →

All datasets StereoSet rt-inod-bias ICAT LLM bias PlantVillage_8px Wiki Neutrality Corpus

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	GPT-2 (small)	ICAT Score	72.97	—	Unverified
2	XLNet (large)	ICAT Score	72.03	—	Unverified
3	GPT-2 (medium)	ICAT Score	71.73	—	Unverified
4	BERT (base)	ICAT Score	71.21	—	Unverified
5	GPT-2 (large)	ICAT Score	70.54	—	Unverified
6	BERT (large)	ICAT Score	69.89	—	Unverified
7	RoBERTa (base)	ICAT Score	67.5	—	Unverified
8	GAL 120B	ICAT Score	65.6	—	Unverified
9	XLNet (base)	ICAT Score	62.1	—	Unverified
10	GPT-3 (text-davinci-002)	ICAT Score	60.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	GPT-4	Best-of	0.5	—	Unverified
2	Baseline	Best-of	0.41	—	Unverified
3	Gemma	Best-of	0.41	—	Unverified
4	Mistral	Best-of	0.36	—	Unverified
5	Llama2	Best-of	0.34	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BAD	ICAT Score	23.44	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RandomForest_default_hyperparameters	Accuracy (%)	49	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	RoBERTa+ALBERT	F1	70.4	—	Unverified