Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
Paper
•
2406.15927
•
Published
•
14
Jannik
jlko
AI & ML interests
None yet
Organizations
None yet
authored
6
papers
over 1 year ago
Estimating the Hallucination Rate of Generative AI
Paper
•
2406.07457
•
Published
•
7
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Paper
•
2106.02584
•
Published
Active Testing: Sample-Efficient Model Evaluation
Paper
•
2103.05331
•
Published
In-Context Learning Learns Label Relationships but Is Not Conventional Learning
Paper
•
2307.12375
•
Published
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Paper
•
2305.16999
•
Published
•
2