Preemptive Detection and Steering of LLM Misalignment via Latent Reachability

RLHF-Umfrage: Kulturelle, multimodale und schnelle KI-Ausrichtung

Detecting Prefix Bias in LLM-based Reward Models

Reward Model Routing in Alignment

MoonshotAI Released Checkpoint-Engine: A Simple Middleware to Update Model Weights in LLM Inference Engines, Effective for Reinforcement Learning

Gemini API File Search: The Easy Way to Build RAG

KnowThyself: Chat-basierte Agentenhilfe für verständliche LLM-Analyse