Co-occurring keywords · papers mentioning both
Papers
Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models
AAAI 2026
Detecting (Un)answerability in Large Language Models with Linear Directions
EACL 2026
From Sampling to Cognition: Modeling Internal Cognitive Confidence in Language Models for Robust Uncertainty Calibration
AAAI 2026
LLMs (Almost) Never Abstain Under Medical Uncertainty
ACL 2026
Characterizing LLM Abstention Behavior in Science QA with Context Perturbations
EMNLP 2024