Not Too Short, Not Too Long: How LLM Response Length Shapes People's Critical Thinking in Error Detection

ArXi:2603.06878v1 Announce Type: new Large language models (LLMs) have become common decision- tools across educational and professional contexts, raising questions about how their outputs shape human critical thinking. Prior work suggests that the amount of AI assistance can influence cognitive engagement, yet little is known about how specific properties of LLM outputs (e.g., response length) impacts users' critical evaluation of information.