Related papers: TRACE: A Metrologically-Grounded Engineering Frame…
Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…
Ensuring Artificial General Intelligence (AGI) reliably avoids harmful behaviors is a critical challenge, especially for systems with high autonomy or in safety-critical domains. Despite various safety assurance proposals and extreme risk…
Growing concerns around the trustworthiness of AI-enabled systems highlight the role of requirements engineering (RE) in addressing emergent, context-dependent properties that are difficult to specify without structured approaches. In this…
Recent advances in Reinforcement Learning (RL) have underscored its potential for incentivizing reasoning capabilities of Large Language Models (LLMs). However, existing step-level efforts suffer from costly annotations that limit domain…
Existing frameworks for LLM-based agent architectures describe systems from a single perspective: industry guides (Anthropic, Google, LangChain) focus on execution topology -- how data flows -- while cognitive science surveys focus on…
We present a novel framework that bridges the gap between the interpretability of decision trees and the advanced reasoning capabilities of large language models (LLMs) to predict startup success. Our approach leverages chain-of-thought…
As AI systems have obtained significant performance to be deployed widely in our daily live and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI…
Prompt engineering has become a production critical component of generative AI systems. However, organizations still lack a shared, auditable method to qualify prompt assets against operational objectives, safety constraints, and compliance…
The popular success of text-based large language models (LLM) has streamlined the attention of the multimodal community to combine other modalities like vision and audio along with text to achieve similar multimodal capabilities. In this…
LLM agents increasingly operate through multi-turn tool use and environment interaction, where safety risks often emerge from intermediate steps long before they surface in the final outcome. Reactive auditing is therefore insufficient:…
Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant…
The convergence of artificial intelligence, cyber-physical systems, and cross-enterprise data ecosystems has propelled industrial intelligence to unprecedented scales. Yet, the absence of a unified trust foundation across data, services,…
Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature. While large language models (LLMs) excel at reasoning over text, they struggle with temporal…
The rationale of this work is based on the current user trust discourse of Artificial Intelligence (AI). We aim to produce novel HCI approaches that use trust as a facilitator for the uptake (or appropriation) of current technologies. We…
Institutional decisions -- regulatory compliance, clinical triage, prior authorization appeal -- require a different AI architecture than general-purpose agents provide. Agent frameworks infer authority conversationally, reconstruct…
Large language model (LLM) based task plans and corresponding human demonstrations for embodied AI may be noisy, with unnecessary actions, redundant navigation, and logical errors that reduce policy quality. We propose an iterative…
The deployment of large language models (LLMs) in production environments has created an urgent need for observability systems that span the full stack -- from model internals to GPU kernels. Yet existing monitoring approaches address…
The adoption of machine learning (ML) and, more specifically, deep learning (DL) applications into all major areas of our lives is underway. The development of trustworthy AI is especially important in medicine due to the large implications…
As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution…
Reasoning in language models is difficult to evaluate: natural-language traces are unverifiable, symbolic datasets are too small, and most benchmarks conflate heuristics with inference. We present FOL-Traces, the first large-scale dataset…