2 papers
cs.CL2026
Diagnosing Correctness Probes under Self-Judgement Confounding
Yi-Long Lu
Hidden-state readouts can predict whether language-model outputs are correct, but objective correctness (OC) usually agrees with the model's own self-judgement (SJ), leaving the de…
cs.AI2026
From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
Yi-Fei Liu, Yi-Long Lu, Di He +1
Psychological constructs within individuals are widely believed to be interconnected. We investigated whether and how Large Language Models (LLMs) can model the correlational struc…