Supervised fine-tuning degrades the correlation between confidence scores and output quality in language models, driven by factors like training distribution similarity rather than true quality.
Predictive uncertainty quantification via risk decompositions for strictly proper scoring rules
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Negative log-likelihood of the greedy-decoded most likely sequence (G-NLL) is a principled single-sequence uncertainty measure for LLMs that achieves state-of-the-art results.
citing papers explorer
-
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Supervised fine-tuning degrades the correlation between confidence scores and output quality in language models, driven by factors like training distribution similarity rather than true quality.
-
Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
Negative log-likelihood of the greedy-decoded most likely sequence (G-NLL) is a principled single-sequence uncertainty measure for LLMs that achieves state-of-the-art results.