Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition
Devesh Tiwari, Camille Davis, Shivank Sinha +3
Linear probes can decode safety-relevant concepts such as truthfulness from language-model activations, but probe accuracy may show only decodability, not that the features the pro…
cs.AI2026
RLHFless: Serverless Computing for Efficient RLHF
Rui Wei, Hanfei Yu, Shubham Jain +5
Reinforcement Learning from Human Feedback (RLHF) has been widely applied to Large Language Model (LLM) post-training to align model outputs with human preferences. Recent models,…