2 citations · 5 across the 5 of their papers we have counts for
3 papers · 1 filter
Rethinking Indirect Prompt Injection as a Test-Time Search Problem
Duong M. Nguyen, Joon Sik Kim, Blazej Manczak +1
We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this…
PrimeGuard: Safe and Helpful LLMs through Tuning-Free Routing
Blazej Manczak, Eliott Zemour, Eric Lin +1
Deploying language models (LMs) necessitates outputs to be both high-quality and compliant with safety guidelines. Although Inference-Time Guardrails (ITG) offer solutions that shi…
CodeIt: Self-Improving Language Models with Prioritized Hindsight Replay
Natasha Butt, Blazej Manczak, Auke Wiggers +4
Large language models are increasingly solving tasks that are commonly believed to require human-level reasoning ability. However, these models still perform very poorly on benchma…