Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases. Geometrically, gender bias is first shown to be captured by a direction in the word embedding. Second, gender neutral words are shown to be linearly separable from gender definition words in the word embedding. Using these properties, we provide a methodology for modifying an embedding to remove gender stereotypes, such as the association between between the words receptionist and female, while maintaining desired associations such as between the words queen and female. We define metrics to quantify both direct and indirect gender biases in embeddings, and develop algorithms to "debias" the embedding. Using crowd-worker evaluation as well as standard benchmarks, we empirically demonstrate that our algorithms significantly reduce gender bias in embeddings while preserving the its useful properties such as the ability to cluster related concepts and to solve analogy tasks. The resulting embeddings can be used in applications without amplifying gender bias.
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.
A framework estimates grammatical gender directions in contextual embeddings via controlled and natural contexts, finding unweighted controlled contexts and centroid estimators yield the purest directions.
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
Developed 19 metamorphic relations to test correlation detection and LSTM forecasting in an outage prediction application, uncovering 8 unknown issues in the live system and detecting 65.9% of injected bugs via mutation testing.
Language models show slight sensitivity to gender perturbations in fairytale QA but gain robustness after fine-tuning on counterfactual anti-stereotypical examples.
citing papers explorer
-
Toward Calibrated, Fair, and accurate Deepfake Detection
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
-
Is She Even Relevant? When BERT Ignores Explicit Gender Cues
A Dutch BERT model encodes gender linearly by epoch 20 but does not dynamically update its representations when explicit female cues contradict learned stereotypical associations in short sentence templates.
-
Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts
A framework estimates grammatical gender directions in contextual embeddings via controlled and natural contexts, finding unweighted controlled contexts and centroid estimators yield the purest directions.
-
Compared to What? Baselines and Metrics for Counterfactual Prompting
Counterfactual prompting effects on LLMs are often indistinguishable from those caused by meaning-preserving paraphrases, causing most previously reported demographic sensitivities to disappear under proper statistical comparison.
-
Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Survey organizes LLM trustworthiness into seven categories and 29 sub-categories, measures eight sub-categories on popular models, and finds that more aligned models generally score higher but with varying effectiveness.
-
Metamorphic Testing of a Deep Learning based Forecaster
Developed 19 metamorphic relations to test correlation detection and LSTM forecasting in an outage prediction application, uncovering 8 unknown issues in the live system and detecting 65.9% of injected bugs via mutation testing.
-
Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts
Language models show slight sensitivity to gender perturbations in fairytale QA but gain robustness after fine-tuning on counterfactual anti-stereotypical examples.