3 papers
cs.CL2026
Do Activation Verbalization Methods Convey Privileged Information?
Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers +2
Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illumi…
cs.AI2026
LLMs Process Lists With General Filter Heads
Arnab Sen Sharma, Giordano Rogers, Natalie Shapira +1
We investigate the mechanisms underlying a range of list-processing tasks in LLMs, and we find that LLMs have learned to encode a compact, causal representation of a general filter…
cs.AI2026
Agents of Chaos
Natalie Shapira, Chris Wendler, Avery Yen +35
We report an exploratory red-teaming study of autonomous language-model-powered agents deployed in a live laboratory environment with persistent memory, email accounts, Discord acc…