3 citations · 3 across the 8 of their papers we have counts for
7 papers · 1 filter
Inducing Emergent Misalignment from Reward Hacks with Iterative DPO
Oliver Daniels, Perusha Moodley, Benjamin M. Marlin +1
Reward hacking during reinforcement learning from verifiable rewards (RLVR) can induce reward seeking and broad misalignment in language models. Studying this misgeneralization is…
Stress-Testing Alignment Audits With Prompt-Level Strategic Deception
Oliver Daniels, Perusha Moodley, Benjamin M. Marlin +1
Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been sys…
ACE and Diverse Generalization via Selective Disagreement
Oliver Daniels, Stuart Armstrong, Alexandre Maranhão +3
Deep neural networks are notoriously sensitive to spurious correlations - where a model learns a shortcut that fails out-of-distribution. Existing work on spurious correlations has…
Enhancing Adaptive Behavioral Interventions with LLM Inference from Participant-Described States
Karine Karine, Benjamin M. Marlin
The use of reinforcement learning (RL) methods to support health behavior change via personalized and just-in-time adaptive interventions is of significant interest to health and b…
Combining LLM decision and RL action selection to improve RL policy for adaptive interventions
Karine Karine, Benjamin M. Marlin
Reinforcement learning (RL) is increasingly being used in the healthcare domain, particularly for the development of personalized health adaptive interventions. Inspired by the suc…
BOTS: Batch Bayesian Optimization of Extended Thompson Sampling for Severely Episode-Limited RL Settings
Karine Karine, Susan A. Murphy, Benjamin M. Marlin
In settings where the application of reinforcement learning (RL) requires running real-world trials, including the optimization of adaptive health interventions, the number of epis…