Deception Abilities Emerged in Large Language Models

Large language models (LLMs) are currently at the forefront of intertwining artificial intelligence (AI) systems with human communication and everyday life. Thus, aligning them with human values is of great importance. However, given the steady increase in reasoning abilities, future LLMs are under suspicion of becoming able to deceive human operators and utilizing this ability to bypass monitoring efforts. As a prerequisite to this, LLMs need to possess a conceptual understanding of deception strategies. This study reveals that such strategies …

artificial artificial intelligence communication cs.ai cs.cl cs.lg deception future human importance intelligence language language models large language large language models life llms operators reasoning systems them values