Dharshan Kumaran

Researchers at Nature Machine Intelligence have identified two competing biases that shape LLM confidence levels: a choice-supportive bias that inflates confidence in initial answers, and a systematic overweighting of contradictory advice that deviates from optimal Bayesian reasoning. The findings reveal that LLM confidence calibration is not simply miscalibrated in one direction, but rather pulled in opposite directions by distinct mechanisms. This dual-bias framework helps explain why LLMs can appear both overconfident and underconfident depending on context, with implications for how we interpret model outputs and design systems that rely on LLM reasoning.