collaborators

11 papers

cs.SE2026

When Policies Change Probabilities: Modular Decision-Making for LLM Code Review

Rasvik Kudum, Max Corbett, Hitansh Paliwal +3

LLM code reviewers often estimate patch risk and make approval decisions in one prompt. A probability should depend on evidence; costs should determine the action taken from it. We…

cs.AI2026

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs

Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov +4

AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untru…

cs.LG2026

Efficient Causal Graph Discovery Using Large Language Models

Thomas Jiralerspong, Xiaoyin Chen, Yash More +2

We propose a novel framework that leverages LLMs for full causal graph discovery. While previous LLM-based methods have used a pairwise query approach, this requires a quadratic nu…

cs.CR2026

Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback

Thomas Jiralerspong, Flemming Kondrup, Yoshua Bengio

Chain-of-thought (CoT) monitoring is proposed as a method for overseeing the internal reasoning of language-model agents. Prior work has shown that when models are explicitly infor…

cs.LG2026

Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes

Aly Kassem, Thomas Jiralerspong, Negar Rostamzadeh +1

Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent…

cs.AI2026

Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs

Thomas Jiralerspong, Trenton Bricken

Model diffing, the process of comparing models' internal representations to identify their differences, is a promising approach for uncovering safety-critical behaviors in new mode…