Metacognition—assessing the quality of one’s own cognitive performance—guides adaptive behaviour across species. Confidence signals can be extracted from language model outputs, yet a fundamental question remains: do models actually use these signals to decide whether to answer or abstain? Here we developed a four-phas...
D. Kumaran, N. Daw, Simon Osindero et al.· Nature Machine Intelligence· 13 citations· ⚡1
It is demonstrated that verbal confidence reflects automatic, sophisticated self-evaluation -- not post-hoc reconstruction -- with implications for understanding metacognition in LLMs and improving calibration.
D. Kumaran, Arthur Conmy, Federico Barbero et al.· arXiv.org· 21 citations· ⚡1
This work proposes XConf (eXperiential Confidence): estimating confidence together with the model's accumulated experience, and sees experiential confidence estimation as a new paradigm for future general-purpose confidence estimation.
Caiqi Zhang, Xiao-Chen Zhu, Chengzu Li et al.· 0 citations
A computational account of confidence in multimodal language models is provided, when answer logits behave as readouts of a latent decision variable is delineated, and statistical decision confidence is established as a unifying framework for studying confidence across biological and artificial intelligence.
D. Kumaran, Viorica Patraucean, M. Ovsjanikov et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
