AINeutralarXiv – CS AI · 3h ago6/10
🧠
Revisiting Anthropomorphic Reflection Markers in Large Language Model Reasoning
Researchers examine how Large Language Models use anthropomorphic reflection markers like 'wait' and 'hmm' during reasoning tasks. The study finds these markers are not uniformly necessary for performance and can often be suppressed without degrading—or even while improving—task outcomes, suggesting they function as surface-level cues rather than indicators of genuine reflection mechanisms.