LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
InThe Eleventh International Conference on Learning Representa- tions, ICLR 2023, Kigali, Rwanda, May 1-5
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
CLUE generates natural language explanations of model uncertainty in fact-checking by unsupervised identification of claim-evidence and inter-evidence conflicts and agreements, followed by prompting and attention steering.
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
GrACE is a fine-tuned generative method that uses similarity to a special token embedding for real-time calibrated confidence in LLMs and enables efficient confidence-based test-time scaling.
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.
citing papers explorer
-
Can LLMs Use Linguistic Uncertainty Markers to Reliably Reflect Intrinsic Confidence?
LLMs struggle to associate epistemic markers with stable internal confidence levels across distributions, even under model-centric interpretations, while maintaining somewhat consistent marker rankings.
-
Explaining Sources of Uncertainty in Automated Fact-Checking
CLUE generates natural language explanations of model uncertainty in fact-checking by unsupervised identification of claim-evidence and inter-evidence conflicts and agreements, followed by prompting and attention steering.
-
Reinforcement Learning with Metacognitive Feedback Elicits Faithful Uncertainty Expression in LLMs
RLMF uses quality of model self-judgments to refine RL rankings and select training data, achieving SOTA faithful calibration while preserving accuracy and outperforming standard RL by up to 63%.
-
Hallucinations Undermine Trust; Metacognition is a Way Forward
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
-
GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models
GrACE is a fine-tuned generative method that uses similarity to a special token embedding for real-time calibrated confidence in LLMs and enables efficient confidence-based test-time scaling.
-
SEAT: Sparse Entity-Aware Tuning for Knowledge Adaptation while Preserving Epistemic Abstention
SEAT preserves epistemic abstention in LLMs during knowledge adaptation via sparse tuning and entity-perturbed KL regularization, yielding 18-101% better abstention on unknown queries while retaining near-perfect knowledge acquisition.