Related papers: PADTHAI-MM: Principles-based Approach for Designin…
Due to the proliferation of short-form content and the rapid adoption of AI, opportunities for deep, reflective thinking have significantly diminished, undermining users' critical thinking and reducing engagement with the reasoning behind…
This paper introduces A2C, a multi-stage collaborative decision framework designed to enable robust decision-making within human-AI teams. Drawing inspiration from concepts such as rejection learning and learning to defer, A2C incorporates…
Large language models (LLMs) have achieved impressive results in natural language understanding, yet their reasoning capabilities remain limited when operating as single agents. Multi-Agent Debate (MAD) has been proposed to address this…
As artificial intelligence (AI) systems approach and surpass expert human performance across a broad range of tasks, obtaining high-quality human supervision for evaluation and training becomes increasingly challenging. Our focus is on…
The rapid proliferation of Generative AI necessitates rigorous documentation standards for transparency and governance. However, manual creation of Model and Data Cards is not scalable, while automated approaches lack large-scale,…
This article presents a modular, component-based architecture for developing and evaluating AI agents that bridge the gap between natural language interfaces and complex enterprise data warehouses. The system directly addresses core…
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements. Recent efforts, therefore, focus on collecting person-related datasets that…
AI systems, in particular with deep learning techniques, have demonstrated superior performance for various real-world applications. Given the need for tailored optimization in specific scenarios, as well as the concerns related to the…
Machine learning approaches often require training and evaluation datasets with a clear separation between positive and negative examples. This risks simplifying and even obscuring the inherent subjectivity present in many tasks. Preserving…
Recent advancements in Large Language Models (LLMs) have substantially evolved Multi-Agent Systems (MASs) capabilities, enabling systems that not only automate tasks but also leverage near-human reasoning capabilities. To achieve this,…
The rise of artificial intelligence (AI) as super-capable assistants has transformed productivity and decision-making across domains. Yet, this integration raises critical concerns about value alignment - ensuring AI behaviors remain…
Unstructured text from legal, medical, and administrative sources offers a rich but underutilized resource for research in public health and the social sciences. However, large-scale analysis is hampered by two key challenges: the presence…
The ideal AI safety moderation system would be both structurally interpretable (so its decisions can be reliably explained) and steerable (to align to safety standards and reflect a community's values), which current systems fall short on.…
As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…
Datasets play a key role in imparting advanced capabilities to artificial intelligence (AI) foundation models that can be adapted to various downstream tasks. These downstream applications can introduce both beneficial and harmful…
Effective feedback, including critique and evaluation, helps designers develop design concepts and refine their ideas, supporting informed decision-making throughout the iterative design process. However, in studio-based design courses,…
Higher education faces growing challenges in delivering personalized, scalable, and pedagogically coherent learning experiences. This study introduces a structured framework for designing an AI-powered Learning Management System (AI-LMS)…
Recent proliferation of powerful AI systems has created a strong need for capabilities that help users to calibrate trust in those systems. As AI systems grow in scale, information required to evaluate their trustworthiness becomes less…
Current large language models (LLMs) excel in verifiable domains where outputs can be checked before action but prove less reliable for high-stakes strategic decisions with uncertain outcomes. This gap, driven by mutually reinforcing…
Value Sensitive Design (VSD) is a framework for integrating human values throughout the technology design process. In parallel, Responsible AI (RAI) advocates for the development of systems aligning with ethical values, such as fairness and…