LLMs Learn to Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions Paper • 2510.08211 • Published Oct 9, 2025 • 22
Iterative Value Function Optimization for Guided Decoding Paper • 2503.02368 • Published Mar 4, 2025 • 15
