Related papers: Detect and Perturb: Neutral Rewriting of Biased an…

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

With widening deployments of natural language processing (NLP) in daily life, inherited social biases from NLP models have become more severe and problematic. Previous studies have shown that word embeddings trained on human-generated…

Recommendation fairness has recently attracted much attention. In the real world, recommendation systems are driven by user behavior, and since users with the same sensitive feature (e.g., gender and age) tend to have the same patterns,…

Quantifying systematic disparities in numerical quantities such as employment rates and wages between population subgroups provides compelling evidence for the existence of societal biases. However, biases in the text written for members of…

Unconscious biases continue to be prevalent in modern text and media, calling for algorithms that can assist writers with bias correction. For example, a female character in a story is often portrayed as passive and powerless ("She…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

The semantically disentangled latent subspace in GAN provides rich interpretable controls in image generation. This paper includes two contributions on semantic latent subspace analysis in the scenario of face generation using StyleGAN2.…

When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…

Selective labels occur when label observations are subject to a decision-making process; e.g., diagnoses that depend on the administration of laboratory tests. We study a clinically-inspired selective label problem called disparate…

Currently, the destruction of the sequence structure in handwritten text has become one of the main bottlenecks restricting the recognition task. The typical situations include additional specific markers (the text swapping modification)…

As natural language processing methods are increasingly deployed in real-world scenarios such as healthcare, legal systems, and social science, it becomes necessary to recognize the role they potentially play in shaping social biases and…

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Toxic content detection aims to identify content that can offend or harm its recipients. Automated classifiers of toxic content need to be robust against adversaries who deliberately try to bypass filters. We propose a method of generating…

Adversarial attacks have gained traction in order to identify potential vulnerabilities in neural ranking models (NRMs), but current attack methods often introduce grammatical errors, nonsensical expressions, or incoherent text fragments,…

Controlled text generation allows for enforcing user-defined constraints on large language model outputs, an increasingly important field as LLMs become more prevalent in everyday life. One common approach uses energy-based decoding, which…

Clothes-changing person re-identification (CC-ReID) aims to recognize individuals under different clothing scenarios. Current CC-ReID approaches either concentrate on modeling body shape using additional modalities including silhouette,…

Temporal grounding aims to localize temporal boundaries within untrimmed videos by language queries, but it faces the challenge of two types of inevitable human uncertainties: query uncertainty and label uncertainty. The two uncertainties…

To create a more inclusive workplace, enterprises are actively investing in identifying and eliminating unconscious bias (e.g., gender, race, age, disability, elitism and religion) across their various functions. We propose a deep learning…

Text classification assigns text to predefined categories. Traditional methods struggle with complex structures and long-range dependencies. Deep learning with recurrent neural networks and Transformer models has improved feature extraction…

There has been increasing interest in evaluations of language models for a variety of risks and characteristics. Evaluations relying on natural language understanding for grading can often be performed at scale by using other language…