Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Subliminal Learning: Language models transmit behavioral traits via hidden signals in data
Alex Cloud, Minh Le, James Chua +5
We study subliminal learning, a surprising phenomenon where language models transmit behavioral traits via semantically unrelated data. In our main experiments, a "teacher" model w…
cs.LG2025
Are DeepSeek R1 And Other Reasoning Models More Faithful?
James Chua, Owain Evans
Language models trained to solve reasoning tasks via reinforcement learning have achieved striking results. We refer to these models as reasoning models. Are the Chains of Thought…
cs.LG2025
Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
James Chua, Jan Betley, Mia Taylor +1
Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignm…