Qingcheng Zeng

@stevezeng7

Final-year PhD on job market / I do agent RL and search / @NorthwesternU @TencentGlobal @Snowflake @AlibabaGroup / Big fan of @Arsenal / Christian

following
followers

Stronger AI capabilities don't automatically mean more reliable confidence

A researcher says his team's EMNLP 2025 papers found that stronger reasoning and vision-language models aren't necessarily more reliable in their confidence; task and modality matter, too.

4 Sources, 39d ago, updated 39d ago

Featured in

Stronger AI capabilities don't automatically mean more reliable confidence

Featured in

Stronger AI capabilities don't automatically mean more reliable confidence