相关论文: DramatVis Personae: Visual Text Analytics for Iden…
Large-scale web-scraped text corpora used to train general-purpose AI models often contain harmful demographic-targeted social biases, creating a regulatory need for data auditing and developing scalable bias-detection methods. Although…
Recent advances in video diffusion models have significantly enhanced text-to-video generation, particularly through alignment tuning using reward models trained on human preferences. While these methods improve visual quality, they can…
Implicit bias may perpetuate healthcare disparities for marginalized patient populations. Such bias is expressed in communication between patients and their providers. We design an ecosystem with guidance from providers to make this bias…
Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first…
The rise of hate speech on online platforms has led to an urgent need for effective content moderation. However, the subjective and multi-faceted nature of hateful online content, including implicit hate speech, poses significant challenges…
With the maturity of visual detection techniques, we are more ambitious in describing visual content with open-vocabulary, fine-grained and free-form language, i.e., the task of image captioning. In particular, we are interested in…
This paper examines the limitations of advanced text-to-image models in accurately rendering unconventional concepts which are scarcely represented or absent in their training datasets. We identify how these limitations not only confine the…
As language models grow in popularity, it becomes increasingly important to clearly measure all possible markers of demographic identity in order to avoid perpetuating existing societal harms. Many datasets for measuring bias currently…
Recent advances in generative AI have enabled visual content creation through text-to-image (T2I) generation. However, despite their creative potential, T2I models often replicate and amplify societal stereotypes -- particularly those…
Heuristics and cognitive biases are an integral part of human decision-making. Automatically detecting a particular cognitive bias could enable intelligent tools to provide better decision-support. Detecting the presence of a cognitive bias…
Images are often termed as representations of perceived reality. As such, racial and gender biases in popular culture and visual media could play a critical role in shaping people's perceptions of society. While previous research has made…
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced reasoning capabilities in Large Language Models. However, adapting RLVR to multimodal domains suffers from a critical \textit{perception-reasoning decoupling}.…
Most research on natural language processing treats bias as an absolute concept: Based on a (probably complex) algorithmic analysis, a sentence, an article, or a text is classified as biased or not. Given the fact that for humans the…
As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…
Paper weakness identification using single-agent or multi-agent LLMs has attracted increasing attention, yet existing approaches exhibit key limitations. Many multi-agent systems simulate human roles at a surface level, missing the…
Voice dictation is increasingly used for text entry, especially in mobile scenarios. However, the speech-based experience gets disrupted when users must go back to a screen and keyboard to review and edit the text. While existing dictation…
Recent advancements in text-to-image generative models have improved narrative consistency in story visualization. However, current story visualization models often overlook cultural dimensions, resulting in visuals that lack authenticity…
Large Language Models (LLMs) are trained primarily on minimally processed web text, which exhibits the same wide range of social biases held by the humans who created that content. Consequently, text generated by LLMs can inadvertently…
Creating meaningful visual narratives through human-AI collaboration requires understanding how text-image intertextuality emerges when textual intentions meet AI-generated visuals. We conducted a three-phase qualitative study with 15…
In micro-blogging platforms, people connect and interact with others. However, due to cognitive biases, they tend to interact with like-minded people and read agreeable information only. Many efforts to make people connect with those who…