Thomas Jiralerspong
Publications
CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
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 untrusted model's trajectory. If the trusted model detects such an intervention, it may infer properties of the monitor and adapt to evade control. We introduce \textbf{CIAware-Bench}, a benchmark for measuring \textbf{c}ontrol \textbf{i}ntervention (CI) awareness across frontier models. CIAware-Bench tests whether models can distinguish their own trajectories from those modified by a control intervention. The benchmark is comprised of a suite of four task domains (essay writing, BigCodeBench, Bash Arena, and SHADE-Arena), while varying trajectory watermarking, side-task presence, and the control protocol. Evaluating eleven frontier models, we find low to moderate CI awareness under default settings (up to 0.87; random chance balanced binary classification accuracy is 0.5) with substantial variation across task domains and model pairs. Detection is generally easier across model families, suggesting that models exploit provider-specific differences in style or post-training. Overall, CI awareness is not a fixed model-level property, and should be measured for each new model release and deployment scenario. We release CIAware-Bench to track CI awareness and inform control protocols whose interventions are harder to detect.
Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
Model diffing, the process of comparing models' internal representations to identify their differences, is a promising approach for uncovering safety-critical behaviors in new models. However, its application has so far been primarily focused on comparing a base model with its finetune. Since new LLM releases are often novel architectures, cross-architecture methods are essential to make model diffing widely applicable. Crosscoders are one solution capable of cross-architecture model diffing but have only ever been applied to base vs finetune comparisons. We provide the first application of crosscoders to cross-architecture model diffing and introduce Dedicated Feature Crosscoders (DFCs), an architectural modification designed to better isolate features unique to one model. Using this technique, we find in an unsupervised fashion features including Chinese Communist Party alignment in Qwen3-8B and Deepseek-R1-0528-Qwen3-8B, American exceptionalism in Llama3.1-8B-Instruct, and a copyright refusal mechanism in GPT-OSS-20B. Together, our results work towards establishing cross-architecture crosscoder model diffing as an effective method for identifying meaningful behavioral differences between AI models.