Richter, Leo

3 publications

ICLR 2026 ContextBench: Modifying Contexts for Targeted Latent Activation and Behaviour Elicitation Robert Graham, Edward Stevinson, Leo Richter, Alexander Chia, Joseph Miller, Joseph Isaac Bloom
ICLR 2025 An Auditing Test to Detect Behavioral Shift in Language Models Leo Richter, Xuanli He, Pasquale Minervini, Matt Kusner
ICMLW 2024 An Auditing Test to Detect Behavioral Shift in Language Models Leo Richter, Nitin Agrawal, Xuanli He, Pasquale Minervini, Matt Kusner