2 papers
cs.AI2025
Interpretable Risk Mitigation in LLM Agent Systems
Jan Chojnacki
Autonomous agents powered by large language models (LLMs) enable novel use cases in domains where responsible action is increasingly important. Yet the inherent unpredictability of…
cs.CL2024
Non-Linear Inference Time Intervention: Improving LLM Truthfulness
Jakub Hoscilowicz, Adam Wiacek, Jan Chojnacki +4
In this work, we explore LLM's internal representation space to identify attention heads that contain the most truthful and accurate information. We further developed the Inference…