相关论文: Social Debiasing for Fair Multi-modal LLMs

Large language models (LLMs) have obtained promising results in mathematical reasoning, which is a foundational skill for human intelligence. Most previous studies focus on improving and measuring the performance of LLMs based on textual…

Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inherent social biases. A typical demonstration is that V-L…

Stereotype biases in Large Multimodal Models (LMMs) perpetuate harmful societal prejudices, undermining the fairness and equity of AI applications. As LMMs grow increasingly influential, addressing and mitigating inherent biases related to…

Deep learning based visual-linguistic multimodal models such as Contrastive Language Image Pre-training (CLIP) have become increasingly popular recently and are used within text-to-image generative models such as DALL-E and Stable…

Textual data used to train large language models (LLMs) exhibits multifaceted bias manifestations encompassing harmful language and skewed demographic distributions. Regulations such as the European AI Act require identifying and mitigating…

Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural…

Visual language models (VLMs) have shown remarkable capabilities in multimodal tasks but face challenges in maintaining fairness across demographic groups, particularly when deployed in federated learning (FL) environments. This paper…

Multilingual Large Language Models (LLMs) offer powerful capabilities for cross-lingual fact-checking. However, these models often exhibit language bias, performing disproportionately better on high-resource languages such as English than…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding. However, extending these models to fine-grained dense prediction tasks, such as semantic segmentation and depth…

Large Language Models (LLMs) offer a promising alternative to traditional survey methods, potentially enhancing efficiency and reducing costs. In this study, we use LLMs to create virtual populations that answer survey questions, enabling…

Background: Large language models (LLMs) are rapidly being integrated into healthcare, promising to enhance various clinical tasks. However, concerns exist regarding their potential for bias, which could compromise patient care and…

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…

Social biases embedded in Large Language Models (LLMs) raise critical concerns, resulting in representational harms -- unfair or distorted portrayals of demographic groups -- that may be expressed in subtle ways through generated language.…

The widespread deployment of Large Language Models (LLMs) has intensified concerns about subtle social biases embedded in their outputs. Existing guardrails often fail when faced with indirect or contextually complex bias-inducing prompts.…

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…

We study the relationship between task-agnostic intrinsic and task-specific extrinsic social bias evaluation measures for Masked Language Models (MLMs), and find that there exists only a weak correlation between these two types of…

Large Language Models (LLMs) have demonstrated remarkable success across various domains. However, despite their promising performance in numerous real-world applications, most of these algorithms lack fairness considerations. Consequently,…

Large Language Models (LLMs) excel in various natural language processing tasks but struggle with hallucination issues. Existing solutions have considered utilizing LLMs' inherent reasoning abilities to alleviate hallucination, such as…

Although large language models (LLMs) are increasingly implicated in interpersonal and societal decision-making, their ability to navigate explicit conflicts between legitimately different cultural value systems remains largely unexamined.…

Social biases can manifest in language agency. However, very limited research has investigated such biases in Large Language Model (LLM)-generated content. In addition, previous works often rely on string-matching techniques to identify…