4 papers · 1 filter
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Anthony +7
Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can…
Steering Language Model Refusal with Sparse Autoencoders
Kyle O'Brien, David Majercak, Xavier Fernandes +7
Responsible deployment of language models requires mechanisms for refusing unsafe prompts while preserving model performance. While most approaches modify model weights through add…
Composable Interventions for Language Models
Arinbjorn Kolbeinsson, Kyle O'Brien, Tianjin Huang +8
Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of n…
Improving Black-box Robustness with In-Context Rewriting
Kyle O'Brien, Nathan Ng, Isha Puri +5
Machine learning models for text classification often excel on in-distribution (ID) data but struggle with unseen out-of-distribution (OOD) inputs. Most techniques for improving OO…