Language Models Prefer What They Know: Relative Confidence Estimation via Confidence Preferences
Paper
•
2502.01126
•
Published
•
4
•
2
Vaishnavi Shrivastava
vshrivas
AI & ML interests
Natural Language Processing, Machine Learning, Prompting, Reasoning
Recent Activity
authored
a paper
about 1 month ago
Language Models Prefer What They Know: Relative Confidence Estimation
via Confidence Preferences
commented on
a paper
about 1 month ago
Language Models Prefer What They Know: Relative Confidence Estimation
via Confidence Preferences
authored
a paper
over 1 year ago
Llamas Know What GPTs Don't Show: Surrogate Models for Confidence
Estimation
Organizations
None yet
vshrivas's activity
commented
a
paper
about 1 month ago