SOTAVerified

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

Showing 111120 of 199 papers

TitleStatusHype
With a Grain of SALT: Are LLMs Fair Across Social Dimensions?0
Inferring bias and uncertainty in camera calibration0
InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics0
Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector0
Investigating Bias in Image Classification using Model Explanations0
Accurate Uncertainty Estimation and Decomposition in Ensemble Learning0
iReason: Multimodal Commonsense Reasoning using Videos and Natural Language with Interpretability0
The Impact of Presentation Style on Human-In-The-Loop Detection of Algorithmic Bias0
Large Language Model (LLM) Bias Index -- LLMBI0
Large-scale news entity sentiment analysis0
Show:102550
← PrevPage 12 of 20Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GPT-2 (small)ICAT Score72.97Unverified
2XLNet (large)ICAT Score72.03Unverified
3GPT-2 (medium)ICAT Score71.73Unverified
4BERT (base)ICAT Score71.21Unverified
5GPT-2 (large)ICAT Score70.54Unverified
6BERT (large)ICAT Score69.89Unverified
7RoBERTa (base)ICAT Score67.5Unverified
8GAL 120BICAT Score65.6Unverified
9XLNet (base)ICAT Score62.1Unverified
10GPT-3 (text-davinci-002)ICAT Score60.8Unverified
#ModelMetricClaimedVerifiedStatus
1GPT-4Best-of0.5Unverified
2BaselineBest-of0.41Unverified
3GemmaBest-of0.41Unverified
4MistralBest-of0.36Unverified
5Llama2Best-of0.34Unverified
#ModelMetricClaimedVerifiedStatus
1BADICAT Score23.44Unverified
#ModelMetricClaimedVerifiedStatus
1RandomForest_default_hyperparametersAccuracy (%)49Unverified
#ModelMetricClaimedVerifiedStatus
1RoBERTa+ALBERTF170.4Unverified