Related papers: VeriMinder: Mitigating Analytical Vulnerabilities …

Vision-language models (VLMs) frequently generate hallucinated content plausible but incorrect claims about image content. We propose a training-free self-correction framework enabling VLMs to iteratively refine responses through…

The generative AI revolution in recent years has been spurred by an expansion in compute power and data quantity, which together enable extensive pre-training of powerful text-to-image (T2I) models. With their greater capabilities to…

While deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset biases, and without deep understanding of…

This dissertation proposes a framework of user-centered security in Natural Language Processing (NLP), and demonstrates how it can improve the accessibility of related research. Accordingly, it focuses on two security domains within NLP…

Large Language Models (LLMs) offer promising opportunities to support mental healthcare workflows, yet they often lack the structured clinical reasoning needed for reliable diagnosis and may struggle to provide the emotionally attuned…

With the advent of multi-modal large language models (MLLMs), datasets used for visual question answering (VQA) and referring expression comprehension have seen a resurgence. However, the most popular datasets used to evaluate MLLMs are…

The ability to extract insights from new data sets is critical for decision making. Visual interactive tools play an important role in data exploration since they provide non-technical users with an effective way to visually compose queries…

NLVR2 (Suhr et al., 2019) was designed to be robust for language bias through a data collection process that resulted in each natural language sentence appearing with both true and false labels. The process did not provide a similar measure…

This study explores the use of LLMs for providing quantitative zero-shot sentiment analysis of implicit software desirability, addressing a critical challenge in product evaluation where traditional review scores, though convenient, fail to…

Tuning machine learning models, particularly deep learning architectures, is a complex process. Automated hyperparameter tuning algorithms often depend on specific optimization metrics. However, in many situations, a developer trades one…

Open-source AI libraries are foundational to modern AI systems, yet they present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance. We introduce LibVulnWatch, a…

Safety alignment is an essential research topic for real-world AI applications. Despite the multifaceted nature of safety and trustworthiness in AI, current safety alignment methods often focus on a comprehensive notion of safety. By…

Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often struggle to capture…

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

We present Verifi2, a visual analytic system to support the investigation of misinformation on social media. On the one hand, social media platforms empower individuals and organizations by democratizing the sharing of information. On the…

A rigorous formalization of desired system requirements is indispensable when performing any verification task. This often limits the application of verification techniques, as writing formal specifications is an error-prone and…

Despite the successes of machine learning (ML) and deep learning (DL) based vulnerability detectors (VD), they are limited to providing only the decision on whether a given code is vulnerable or not, without details on what part of the code…

Deep neural networks are increasingly employed in high-stakes medical applications, despite their tendency for shortcut learning in the presence of spurious correlations, which can have potentially fatal consequences in practice. Whereas a…

Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the…

Natural Language to SQL (NL2SQL) has seen significant advancements with large language models (LLMs). However, these models often depend on closed-source systems and high computational resources, posing challenges in data privacy and…