相关论文: Gender Bias in Explainability: Investigating Perfo…

As Large Language Models (LLMs) become increasingly powerful and accessible to human users, ensuring fairness across diverse demographic groups, i.e., group fairness, is a critical ethical concern. However, current fairness and bias…

As the applications of Natural Language Processing (NLP) in sensitive areas like Political Profiling, Review of Essays in Education, etc. proliferate, there is a great need for increasing transparency in NLP models to build trust with…

Explanation methods and their evaluation have become a significant issue in explainable artificial intelligence (XAI) due to the recent surge of opaque AI models in decision support systems (DSS). Since the most accurate AI models are…

In recent times, there have been increasing accusations on artificial intelligence systems and algorithms of computer vision of possessing implicit biases. Even though these conversations are more prevalent now and systems are improving by…

Even as we engineer LLMs for alignment and safety, they often uncover biases from pre-training data's statistical regularities (from disproportionate co-occurrences to stereotypical associations mirroring human cognitive biases). This leads…

Our society is plagued by several biases, including racial biases, caste biases, and gender bias. As a matter of fact, several years ago, most of these notions were unheard of. These biases passed through generations along with…

Understanding and removing bias from the decisions made by machine learning models is essential to avoid discrimination against unprivileged groups. Despite recent progress in algorithmic fairness, there is still no clear answer as to which…

Recent works have shown considerable improvements in task-oriented dialogue (TOD) systems by utilizing pretrained large language models (LLMs) in an end-to-end manner. However, the biased behavior of each component in a TOD system and the…

With language models becoming increasingly ubiquitous, it has become essential to address their inequitable treatment of diverse demographic groups and factors. Most research on evaluating and mitigating fairness harms has been concentrated…

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

Code language models are increasingly adopted for both understanding and generative tasks. Despite their success, these models frequently produce overconfident incorrect predictions and underconfident correct predictions, undermining their…

As complex machine learning models continue to find applications in high-stakes decision-making scenarios, it is crucial that we can explain and understand their predictions. Post-hoc explanation methods provide useful insights by…

Speech emotion recognition (SER) systems often exhibit gender bias. However, the effectiveness and robustness of existing debiasing methods in such multi-label scenarios remain underexplored. To address this gap, we present EMO-Debias, a…

Deep Learning methods are renowned for their performances, yet their lack of interpretability prevents them from high-stakes contexts. Recent model agnostic methods address this problem by providing post-hoc interpretability methods by…

Double-blind peer review mechanism has become the skeleton of academic research across multiple disciplines including computer science, yet several studies have questioned the quality of peer reviews and raised concerns on potential biases…

Mitigating bias in training on biased datasets is an important open problem. Several techniques have been proposed, however the typical evaluation regime is very limited, considering very narrow data conditions. For instance, the effect of…

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

Large pre-trained language models have become a crucial backbone for many downstream tasks in natural language processing (NLP), and while they are trained on a plethora of data containing a variety of biases, such as gender biases, it has…

Machine learning systems exhibit diverse failure modes: unfairness toward protected groups, brittleness to spurious correlations, poor performance on minority sub-populations, which are typically studied in isolation by distinct research…

The popularity of pretrained language models in natural language processing systems calls for a careful evaluation of such models in down-stream tasks, which have a higher potential for societal impact. The evaluation of such systems…