What are you looking for?

Two Axes of LLM Abstention: Answer Correctness and Question Answerability🔥 hot

AI·Across five instruction-tuned LLMs, ordinary answer-confidence separates correct from wrong answers on answerable questions but fails to distinguish unanswerable questions (e.g., false-premise ones in CREPE), while a linear probe on hidden states performs the opposite, revealing two distinct abstention axes that remain separable even at 14B scale.

What LLM Forecasters Know but Don't Say: Probing Internal Representations for Calibration and Faithfulness

AI·The paper probes internal representations of Eternis-Forecaster 8B for forecasting, training a representation-pooling method to assess calibration and faithfulness of internal CoT reasoning.

TypeProbe: Recovering Type Representations from Hidden States of Pre-trained Code Models

AI·TypeProbe recovers type representations from hidden states of pretrained code models using parallel Java and Python datasets.