相关论文: Bias Analysis and Mitigation through Protected Att…

Vision-language models (VLMs) have gained widespread adoption in both industry and academia. In this study, we propose a unified framework for systematically evaluating gender, race, and age biases in VLMs with respect to professions. Our…

As language models (LMs) become increasingly powerful and widely used, it is important to quantify them for sociodemographic bias with potential for harm. Prior measures of bias are sensitive to perturbations in the templates designed to…

As generative large language models (LLMs) grow more performant and prevalent, we must develop comprehensive enough tools to measure and improve their fairness. Different prompt-based datasets can be used to measure social bias across…

The advancement of large language models (LLMs) has demonstrated strong capabilities across various applications, including mental health analysis. However, existing studies have focused on predictive performance, leaving the critical issue…

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Drawing parallels between human cognition and artificial intelligence, we explored how large language models (LLMs) internalize identities imposed by targeted prompts. Informed by Social Identity Theory, these identity assignments lead LLMs…

Large language models (LLMs) have shown remarkable adaptability to diverse tasks, by leveraging context prompts containing instructions, or minimal input-output examples. However, recent work revealed they also exhibit label bias -- an…

This paper explores the design of a propaganda detection tool using Large Language Models (LLMs). Acknowledging the inherent biases in AI models, especially in political contexts, we investigate how these biases might be leveraged to…

Warning: This paper contains content that may be offensive or upsetting. There has been a significant increase in the usage of large language models (LLMs) in various applications, both in their original form and through fine-tuned…

Large language models (LLMs) are known to generate politically biased text. Yet, it remains unclear how such biases arise, making it difficult to design effective mitigation strategies. We hypothesize that these biases are rooted in the…

Dataset bias is a significant problem in training fair classifiers. When attributes unrelated to classification exhibit strong biases towards certain classes, classifiers trained on such dataset may overfit to these bias attributes,…

Large Language Models (LLMs) are increasingly integral to information dissemination and decision-making processes. Given their growing societal influence, understanding potential biases, particularly within the political domain, is crucial…

Large language models (LLMs), including ChatGPT, can extract profitable trading signals from the sentiment in news text. However, backtesting such strategies poses a challenge because LLMs are trained on many years of data, and backtesting…

Numerous types of social biases have been identified in pre-trained language models (PLMs), and various intrinsic bias evaluation measures have been proposed for quantifying those social biases. Prior works have relied on human annotated…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Reference texts such as encyclopedias and news articles can manifest biased language when objective reporting is substituted by subjective writing. Existing methods to detect bias mostly rely on annotated data to train machine learning…

Research has shown that while large language models (LLMs) can generate their responses based on cultural context, they are not perfect and tend to generalize across cultures. However, when evaluating the cultural bias of a language…

Published research highlights the presence of demographic bias in automated facial attribute classification. The proposed bias mitigation techniques are mostly based on supervised learning, which requires a large amount of labeled training…

Machine learning is a promising approach to visualization recommendation due to its high scalability and representational power. Researchers can create a neural network to predict visualizations from input data by training it over a corpus…

With the advent of Large Language Models (LLMs) possessing increasingly impressive capabilities, a number of Large Vision-Language Models (LVLMs) have been proposed to augment LLMs with visual inputs. Such models condition generated text on…