16 citations · 17 across the 7 of their papers we have counts for
3 papers · 1 filter
Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits
Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani +3
The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during m…
Limitations of Agents Simulated by Predictive Models
Raymond Douglas, Jacek Karwowski, Chan Bae +2
There is increasing focus on adapting predictive models into agent-like systems, most notably AI assistants based on language models. We outline two structural reasons for why thes…
Mitigating the Influence of Distractor Tasks in LMs with Prior-Aware Decoding
Raymond Douglas, Andis Draguns, Tomáš Gavenčiak
The broad capabilities of Language Models (LMs) can be limited by their sensitivity to distractor tasks: LMs can infer secondary tasks from the prompt in addition to the intended o…