182 citations · 204 across the 11 of their papers we have counts for
7 papers · 1 filter
Interpreting Model Reasoning through Behavioral Counterfactuals
Shawn Im, James Oldfield, Adel Bibi +1
Faithfully understanding the internal process that occurs as models form their chain of thought is an important problem with the rise in model capabilities. However, this remains c…
How Much Do Activation Monitors Benefit from Original Model Computations?
James Oldfield, Shawn Im, Jay J Culligan +3
One powerful way to safeguard AI systems is to monitor their internal computations--where signs of undesirable behavior might be more easily detectable than from models' inputs and…
Towards a Unified Misuse Monitoring Benchmark
Aniruddh Pramod, James Oldfield, Adel Bibi
LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-r…
BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents
Ziyan Wang, Shuqing Shi, James Oldfield +5
In decentralized consumer-to-consumer (C2C) marketplaces, people list goods, negotiate with strangers, and rate one another, so trust rests on reputation. Large language model (LLM…
-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation Signals
Aoxi Liu, Yupeng Chen, James Oldfield +5
Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring for D-LLMs remains largely…
fmxcoders: Factorized Masked Crosscoders for Cross-Layer Feature Discovery
Andreas D. Demou, Panagiotis Koromilas, James Oldfield +2
Many features in pretrained Transformers span multiple layers: they emerge through stages of inference, persist in the residual stream, or are built jointly by parallel MLPs. Cross…
PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding
Panagiotis Koromilas, Andreas D. Demou, James Oldfield +2
Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine a…