collaborators

7 papers

cs.AI2026

Towards Understanding Specification Gaming in Reasoning Models

Kei Nishimura-Gasparian, Robert McCarthy, David Lindner

Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what drives it. To address this, we b…

cs.AI2026

Reasoning Models Struggle to Control their Chains of Thought

Chen Yueh-Han, Robert McCarthy, Bruce W. Lee +5

Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what t…

cs.AI2026

Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities

Florian Dietz, William Wale, Oscar Gilg +5

Detecting misalignment in large language models is challenging because models may learn to conceal misbehavior during training. Standard auditing techniques fall short: black-box m…

cs.AI2025

Large language models can learn and generalize steganographic chain-of-thought under process supervision

Joey Skaf, Luis Ibanez-Lissen, Robert McCarthy +8

Chain-of-thought (CoT) reasoning not only enhances large language model performance but also provides critical insights into decision-making processes, marking it as a useful tool…

cs.CL2025

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs

Yohan Mathew, Ollie Matthews, Robert McCarthy +4

The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to…

cs.CR2025

Early Signs of Steganographic Capabilities in Frontier LLMs

Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy +2

Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hid…