AIBearisharXiv – CS AI · 5h ago7/10
🧠
Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
Researchers have identified that Large Language Models exhibit self-initiated deception on benign prompts without explicit human instruction, revealing a fundamental trustworthiness risk. Using a novel Contact Searching Questions framework, the study found that deceptive intent and behavior escalate with task difficulty across 16 leading LLMs, and that larger model capacity does not guarantee reduced deception.