Related papers: When Evaluation Becomes a Side Channel: Regime Lea…
Drawing on constructs from psychology, prior work has identified a distinction between explicit and implicit bias in large language models (LLMs). While many LLMs undergo post-training alignment and safety procedures to avoid expressions of…
As large language models (LLMs) are increasingly deployed in high-stakes and operational settings, evaluation strategies based solely on aggregate accuracy are often insucient to characterize system reliability. This study proposes a…
Understanding the agent's learning process, particularly the factors that contribute to its success or failure post-training, is crucial for comprehending the rationale behind the agent's decision-making process. Prior methods clarify the…
We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of…
This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the…
Reinforcement learning policies are typically represented by black-box neural networks, which are non-interpretable and not well-suited for safety-critical domains. To address both of these issues, we propose constrained normalizing flow…
The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from…
Data leakage is a well-known problem in machine learning. Data leakage occurs when information from outside the training dataset is used to create a model. This phenomenon renders a model excessively optimistic or even useless in the real…
Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…
The influence of Artificial Intelligence (AI), and specifically Large Language Models (LLM), on education is continuously increasing. These models are frequently used by students, giving rise to the question whether current forms of…
As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…
As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…
Regression is a fundamental prediction task common in data-centric engineering applications that involves learning mappings between continuous variables. In many engineering applications (e.g.\ structural health monitoring), feature-label…
The growing integration of Large Language Models (LLMs) into critical societal domains has raised concerns about embedded biases that can perpetuate stereotypes and undermine fairness. Such biases may stem from historical inequalities in…
Large language models can recognize when they are being evaluated (evaluation awareness) and behave differently because of that, which undermines the validity of safety and alignment benchmarks. We propose LURE (Live-Usage Replay…
As AI adoption expands across human society, the problem of aligning AI models to match human preferences remains a grand challenge. Currently, the AI alignment field is deeply divided between behavioral and representational approaches,…
The rapid integration of conversational AI systems into educational settings has intensified ethical concerns about academic integrity, fairness, and students' cognitive development. Institutional responses have largely centered on AI…
Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…
A central prediction of the accompanying theoretical framework is that metacognitive calibration can vary even when content-level performance is held approximately fixed, depending on whether support structure is preserved in a globally…
As LLMs become embedded in research workflows and organizational decision processes, their effect on analytical reliability remains uncertain. We distinguish two dimensions of analytical reliability -- intelligence (the capacity to reach…