A logit-based method converts an LLM's numeric guesses into a calibrated prior over Pearson correlations and ranks expert-flagged hypotheses better than ranking by magnitude or by a fine-tuned RoBERTa classifier.
Aleatory or epistemic? does it matter?Structural Safety, 31(2):105–112, 2009
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior
A logit-based method converts an LLM's numeric guesses into a calibrated prior over Pearson correlations and ranks expert-flagged hypotheses better than ranking by magnitude or by a fine-tuned RoBERTa classifier.