相关论文: Identifying and Mitigating Gender Bias in Hyperbol…

Despite their prevalence in society, social biases are difficult to identify, primarily because human judgements in this domain can be unreliable. We take an unsupervised approach to identifying gender bias against women at a comment level…

We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these "Winogender schemas," we evaluate…

When we train models on biased datasets, they not only reproduce data biases, but can worsen them at test time - a phenomenon called bias amplification. Many of the current bias amplification metrics (e.g., BA (MALS), DPA) measure bias…

Recent works have found evidence of gender bias in models of machine translation and coreference resolution using mostly synthetic diagnostic datasets. While these quantify bias in a controlled experiment, they often do so on a small scale…

Backward compatible representation learning enables updated models to integrate seamlessly with existing ones, avoiding to reprocess stored data. Despite recent advances, existing compatibility approaches in Euclidean space neglect the…

Background: Existing clinical prediction models often represent patient data using features that ignore the semantic relationships between clinical concepts. This study integrates domain-specific semantic information by mapping the SNOMED…

Gender bias is a significant issue in machine translation, leading to ongoing research efforts in developing bias mitigation techniques. However, most works focus on debiasing bilingual models without much consideration for multilingual…

Bolukbasi et al. (2016) presents one of the first gender bias mitigation techniques for word representations. Their method takes pre-trained word representations as input and attempts to isolate a linear subspace that captures most of the…

Visual geolocalization, the task of predicting where an image was taken, remains challenging due to global scale, visual ambiguity, and the inherently hierarchical structure of geography. Existing paradigms rely on either large-scale…

Large language models (LLMs) have revolutionized natural language processing, yet their practical utility is often limited by persistent issues of hallucinations and outdated parametric knowledge. Although post-training model editing offers…

We introduce ManifoldMind, a probabilistic geometric recommender system for exploratory reasoning over semantic hierarchies in hyperbolic space. Unlike prior methods with fixed curvature and rigid embeddings, ManifoldMind represents users,…

Recent advancements in text-to-image diffusion models have shown remarkable creative capabilities with textual prompts, but generating personalized instances based on specific subjects, known as subject-driven generation, remains…

Many high-dimensional and large-volume data sets of practical relevance have hierarchical structures induced by trees, graphs or time series. Such data sets are hard to process in Euclidean spaces and one often seeks low-dimensional…

This paper presents a new method for automatically detecting words with lexical gender in large-scale language datasets. Currently, the evaluation of gender bias in natural language processing relies on manually compiled lexicons of…

Research on bias in Text-to-Image (T2I) models has primarily focused on demographic representation and stereotypical attributes, overlooking a fundamental question: how does grammatical gender influence visual representation across…

We introduce a novel relaxation strategy for denoising hyperbolic-valued data. The main challenge is here the non-convexity of the hyperbolic sheet. Instead of considering the denoising problem directly on the hyperbolic space, we exploit…

Machine unlearning methods have become increasingly important for selective concept removal in large pre-trained models. While recent work has explored unlearning in Euclidean contrastive vision-language models, the effectiveness of concept…

Various measures have been proposed to quantify human-like social biases in word embeddings. However, bias scores based on these measures can suffer from measurement error. One indication of measurement quality is reliability, concerning…

Clinical word embeddings are extensively used in various Bio-NLP problems as a state-of-the-art feature vector representation. Although they are quite successful at the semantic representation of words, due to the dataset - which…

Intrinsic image decomposition aims to estimate physically based rendering (PBR) parameters such as albedo, roughness, and metallicity from images. While recent methods achieve strong single-view predictions, applying them independently to…