DiFair: A Benchmark for Disentangled Assessment of Gender Knowledge and Bias
Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its predictions. Importantly, this evaluation protocol overlooks the possible adverse impact of bias mitigation on useful gender knowledge. To fill this gap, we propose DiFair, a manually curated dataset based on masked language modeling objectives. DiFair allows us to introduce a unified metric, gender invariance score, that not only quantifies a model's biased behavior, but also checks if useful gender knowledge is preserved. We use DiFair as a benchmark for a number of widely-used pretained language models and debiasing techniques. Experimental results corroborate previous findings on the existing gender biases, while also demonstrating that although debiasing techniques ameliorate the issue of gender bias, this improvement usually comes at the price of lowering useful gender knowledge of the model.
Code (1)
Tasks
Language ModelingLanguage ModellingMasked Language ModelingSimilar Papers 제목 키워드 기반
GKnow: Measuring the Entanglement of Gender Bias and Factual Gender
Recent works have analyzed the impact of individual components of neural networks on gendered predictions, often with a focus on mitigating gender bias. However, mechanistic interpretations of gender tend to (i) focus on…
GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those related to gender. In response to this i…
counterfactualData AugmentationFairnessText GenerationProtecting gender and identity with disentangled speech representations
Besides its linguistic content, our speech is rich in biometric information that can be inferred by classifiers. Learning privacy-preserving representations for speech signals enables downstream tasks without sharing unn…
Privacy PreservingRepresentation LearningSpeaker VerificationSpeech RecognitionLearning Disentangled Speech Representations
Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeec…
BenchmarkingDisentanglementInformativenessRepresentation Learning+1Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation
Gender bias in vision-language foundation models (VLMs) raises concerns about their safe deployment and is typically evaluated using benchmarks with gender annotations on real-world images. However, as these benchmarks o…