Research on dualities in geometric stereotypes.
problem Understanding dualities in geometric stereotypes.
method Continuation of previous research on stereotype spaces and algebras.
result New insights into geometric stereotype dualities.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
169,051 papers · 148 categories
Trend · papers per month
30 results for “stereotyping”
Machine learning algorithms are optimized to model statistical properties of the training data. If the input data reflects stereotypes and biases of the broader society, then the output of the learning algorithm also captures these stereotypes. In this paper, we initiate the study of gender stereotypes in {\em word emb…
The paper formalizes stereotyping in representation and proposes mitigation strategies.
problem Stereotyping in representation and its impact on allocation.
method Formalization of stereotyping, machine learning pipeline analysis, and mitigation strategies.
result Demonstrated effectiveness of mitigation strategies on synthetic datasets.
New method labels GAN-generated faces without stereotyping.
problem Eliminating human bias in AI classification of fictional faces.
method Penalized regression to minimize cost function between realistic and target images.
result Successfully labels GAN-generated images without stereotyping.
Most animals possess the ability to actuate a vast diversity of movements, ostensibly constrained only by morphology and physics. In practice, however, a frequent assumption in behavioral science is that most of an animal's activities can be described in terms of a small set of stereotyped motifs. Here we introduce a m…
Study examines bias in language models across multiple languages.
problem Assessing bias in language models across different languages.
method Semi-automatically translated data sets into multiple languages, analyzed mono- and multilingual models.
result Notable differences in bias across languages, with Turkish models showing least stereotypes.
New method debiases word embeddings for multiclass settings like race and religion.
problem Word embeddings in online texts perpetuate human stereotypes, including race and religion.
method Proposes a novel methodology to debias word embeddings in multiclass settings.
result Demonstrates robust multiclass debiasing that maintains NLP task efficacy.
Autism Spectrum Disorders (ASDs) are often associated with specific atypical postural or motor behaviors, of which Stereotypical Motor Movements (SMMs) have a specific visibility. While the identification and the quantification of SMM patterns remain complex, its automation would provide support to accurate tuning of t…
Introduces MPR to measure and optimize representation across intersectional groups in retrieval.
problem Harmful stereotypes, cultural erasure, and social disparities in image search and retrieval.
method Develops MPR metric, practical estimation methods, theoretical guarantees, and optimization algorithms.
result Optimizing MPR yields more proportional representation across multiple intersectional groups, often with minimal retrieval accuracy compromise.
New method to understand bias in word embeddings.
problem Understanding and mitigating bias in word embeddings.
method Developed a technique to trace bias origins back to training documents.
result Accurate approximations of bias reduction can be made.
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 traine…
Algorithms are increasingly used to aid, or in some cases supplant, human decision-making, particularly for decisions that hinge on predictions. As a result, two additional features in addition to prediction quality have generated interest: (i) to facilitate human interaction and understanding with these algorithms, we…
Word embedding models have become a fundamental component in a wide range of Natural Language Processing (NLP) applications. However, embeddings trained on human-generated corpora have been demonstrated to inherit strong gender stereotypes that reflect social constructs. To address this concern, in this paper, we propo…
Large language models struggle with causal relationships, leading to biases and hallucinations.
problem LLMs struggle with true causal relationships, leading to biases and hallucinations.
method Embed causality into LLMs training process at every stage.
result LLMs need to be trained to understand and apply causal knowledge, not just recite it.
We introduce normalized nonnegative models (NNM) for explorative data analysis. NNMs are partial convexifications of models from probability theory. We demonstrate their value at the example of item recommendation. We show that NNM-based recommender systems satisfy three criteria that all recommender systems should ide…
We are interested in estimating individual labels given only coarse, aggregated signal over the data points. In our setting, we receive sets ("bags") of unlabeled instances with constraints on label proportions. We relax the unrealistic assumption of known label proportions, made in previous work; instead, we assume on…
Cortical circuits exhibit intricate recurrent architectures that are remarkably similar across different brain areas. Such stereotyped structure suggests the existence of common computational principles. However, such principles have remained largely elusive. Inspired by gated-memory networks, namely long short-term me…
New method reduces gender bias in language models without harming performance.
problem Bias in language models learned from biased data.
method Causal analysis to identify problematic model components, followed by linear projection of weight matrices.
result DAMA significantly decreases bias in language models while maintaining performance.
Equal experience fairness in recommender systems reduces bias.
problem Bias in data leads to unfair item recommendations.
method Introduces equal experience fairness notion and optimization framework.
result Mitigates unfairness in recommendations with minimal accuracy loss.
An Analysis of the Effects of Decoding Algorithms on Fairness in Open-Ended Language Generationcs.CL
Study examines how decoding algorithms affect fairness in language generation models.
problem Impact of decoding algorithms on fairness in open-ended language generation.
method Systematic analysis of top-, top-, and temperature decoding algorithms.
result Decoding algorithms significantly impact fairness across demographic groups.
Unified causal model improves controllable text generation without bias.
problem Controllable text generation tasks, biased by prior models.
method Unified causal framework for attribute-conditional generation and text attribute transfer.
result Significant superiority over previous conditional models for improved control and reduced bias.
Paper finds gender classification accuracy varies by skin type, not ethnicity.
problem Unequal performance of face classification services across skin types and genders.
method Stability experiments, image manipulation, and post-hoc explanation techniques.
result Lip, eye, and cheek structure differences, not skin type, cause gender classification discrepancies.
New method removes bias from data while maintaining accuracy.
problem Reduces bias in machine learning models while maintaining accuracy.
method Geometric method that removes correlations between data and protected variables.
result Debiased features are more accurate and fair than state-of-the-art algorithms.
Study on memorization vs. generalization in overparameterized networks.
problem Understanding the trade-off between memorization and generalization in neural networks.
method Examined fully-connected and convolutional networks trained to minimize reconstruction error.
result Different architectures exhibit distinct inductive biases, affecting generalization from a single training example.
Normalized nonnegative models assign probability distributions to users and random variables to items; see [Stark, 2015]. Rating an item is regarded as sampling the random variable assigned to the item with respect to the distribution assigned to the user who rates the item. Models of that kind are highly expressive. F…
The paper uses learned prototypes to explain deep learning models for time-series data.
problem Lack of explainable AI in deep learning models for high-risk decisions.
method Learned prototypes in latent space of deep learning models.
result Prototypes improve classification decisions and provide explainable insights.
Study proposes an alternative method to measure societal biases using smoothed co-occurrence relations.
problem Measuring societal biases using word embeddings can introduce irrelevant concepts.
method Proposes an alternative approach using smoothed first-order co-occurrence relations.
result First-order approach shows higher correlations with actual gender bias statistics.
Paper tackles underranking in group-fair ranking systems, proving a trade-off and presenting an algorithm.
problem Underranking in group-fair ranking systems can worsen social and economic inequalities.
method Formulated underranking as a new problem, proved a lower bound, and presented a fair ranking algorithm.
result Algorithm achieves best of underranking and group fairness, confirming theoretical trade-off.
Behaviors of several laboratory animals can be modeled as sequences of stereotyped behaviors, or behavioral motifs. However, identifying such motifs is a challenging problem. Behaviors have a multi-scale structure: the animal can be simultaneously performing a small-scale motif and a large-scale one (e.g. \textit{chewi…
MAPPING debiases GNNs for fair node classification with limited leakage.
problem Graph Neural Networks inherit and exacerbate historical discrimination in high-stake domains.
method MAPPING uses distance covariance-based fairness constraints and adversarial debiasing.
result MAPPING achieves better trade-offs between fairness and utility, mitigating privacy risks.