English
Related papers

Related papers: Realistic honeypot evaluations for scheming propen…

200 papers

Recent work has shown how predictive modeling can endow agents with rich knowledge of their surroundings, improving their ability to act in complex environments. We propose question-answering as a general paradigm to decode and understand…

Agents built on vision-language models increasingly face tasks that demand anticipating future states rather than relying on short-horizon reasoning. Generative world models offer a promising remedy: agents could use them as external…

Artificial Intelligence · Computer Science 2026-01-09 Cheng Qian , Emre Can Acikgoz , Bingxuan Li , Xiusi Chen , Yuji Zhang , Bingxiang He , Qinyu Luo , Dilek Hakkani-Tür , Gokhan Tur , Yunzhu Li , Heng Ji

Safety cases for frontier AI systems should provide a convincing argument, supported by evidence, that the risk of harm is within an acceptable bound. When developers author their own safety cases, confirmation bias and conflicted…

An important feature of pervasive, intelligent assistance systems is the ability to dynamically adapt to the current needs of their users. Hence, it is critical for such systems to be able to recognize those goals and needs based on…

Artificial Intelligence · Computer Science 2023-01-16 Nils Wilken , Lea Cohausz , Johannes Schaum , Stefan Lüdtke , Heiner Stuckenschmidt

LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process is poorly understood. Existing faithfulness metrics have critical limitations, typically relying on…

Artificial Intelligence · Computer Science 2026-02-04 Harry Mayne , Justin Singh Kang , Dewi Gould , Kannan Ramchandran , Adam Mahdi , Noah Y. Siegel

AI alignment is often framed as the task of ensuring that an AI system follows a set of stated principles or human preferences, but general principles rarely determine their own application in concrete cases. When principles conflict, when…

Artificial Intelligence · Computer Science 2026-04-14 Behrooz Razeghi

In many societal resource allocation domains, machine learning methods are increasingly used to either score or rank agents in order to decide which ones should receive either resources (e.g., homeless services) or scrutiny (e.g., child…

Multiagent Systems · Computer Science 2020-12-17 Andrew Estornell , Sanmay Das , Yevgeniy Vorobeychik

Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based…

Machine Learning · Computer Science 2021-11-10 Stefan Radic Webster , Peter Flach

A growing body of research runs human subject evaluations to study whether providing users with explanations of machine learning models can help them with practical real-world use cases. However, running user studies is challenging and…

Human-Computer Interaction · Computer Science 2022-08-23 Valerie Chen , Nari Johnson , Nicholay Topin , Gregory Plumb , Ameet Talwalkar

Static benchmarks capture only part of how large language models behave in practice. Real systems place models inside repeated loops with time limits, formatting constraints, and failure modes. We study this setting in a timed multi-phase…

Artificial Intelligence · Computer Science 2026-05-22 H. C. Ekne

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely,…

Computation and Language · Computer Science 2024-07-16 Jérémy Scheurer , Mikita Balesni , Marius Hobbhahn

Even when a tool is explicitly described as unfair and harmful to others, ostensibly safety-aligned LLM agents still voluntarily engage in secret collusion whenever doing so confers a strategic advantage. To investigate this phenomenon, we…

Artificial Intelligence · Computer Science 2026-05-28 Xijie Zeng , Frank Rudzicz

We investigate the real-time estimation of human situation awareness using observations from a robot teammate with limited visibility. In human factors and human-autonomy teaming, it is recognized that individuals navigate their…

Robotics · Computer Science 2025-02-13 Jack Kolb , Karen M. Feigh

With the widespread availability of LLMs since the release of ChatGPT and increased public scrutiny, commercial model development appears to have focused their efforts on 'safety' training concerning legal liabilities at the expense of…

Computation and Language · Computer Science 2024-08-02 Alina Leidinger , Richard Rogers

Whether in agentic workflows, social studies, or chat settings, large language models (LLMs) are increasingly being asked to replace humans in choosing which goals to pursue, rather than completing predefined tasks. However, the assumption…

Computation and Language · Computer Science 2026-05-14 Gaia Molinaro , Dave August , Danielle Perszyk , Anne G. E. Collins

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Bayesian optimization has emerged as a powerful strategy to accelerate scientific discovery by means of autonomous experimentation. However, expensive measurements are required to accurately estimate materials properties, and can quickly…

Machine Learning · Statistics 2021-03-08 Riley J. Hickman , Florian Häse , Loïc M. Roch , Alán Aspuru-Guzik

Predictive distributions quantify uncertainties ignored by point estimates. This paper introduces The Neural Testbed: an open-source benchmark for controlled and principled evaluation of agents that generate such predictions. Crucially, the…

Recent approaches to goal recognition have leveraged planning landmarks to achieve high-accuracy with low runtime cost. These approaches, however, lack a probabilistic interpretation. Furthermore, while most probabilistic models to goal…

Artificial Intelligence · Computer Science 2021-02-24 Kin Max Gusmão , Ramon Fraga Pereira , Felipe Meneguzzi

Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or faithfully solving the intended problem. We study this phenomenon in a generic machine…

General Economics · Economics 2026-04-27 Xiaoyun Qiu , Yang Yu , Haifeng Xu