AINeutralarXiv – CS AI · Mar 177/10
🧠
LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy
Researchers applied Signal Detection Theory to analyze three large language models across 168,000 trials, finding that temperature parameter changes both sensitivity and response bias simultaneously. The study reveals that traditional calibration metrics miss important diagnostic information that SDT's full parametric framework can provide.