List your company

Hallucination Detection on FOIL (Reference-Conditioned Accuracy)

98.4Accuracy (4 Refs)Ref-FLEUR
69.2876.8484.491.96Mar 21, 2023Sep 5, 2023Feb 20, 2024Aug 7, 2024Jan 22, 2025Jul 9, 2025Dec 25, 2025

Evaluation results

MethodLinks
Ref-FLEURReference-based=true2025.1298.497.3
Ref-G-VEvalReference-based=true2025.1298.497.8
PearlReference-based=true, Backbone=ViT-B/322025.1297.296.5
Ref-HICEScoreReference-based=true2025.129796.4
FLEURReference-based=false2025.1296.896.8
PearlReference-based=false, Backbone=ViT-B/322025.1296.796.7
DENEBReference-based=true, Backbone=ViT-B/322025.1296.195.1
PolosReference-based=true2025.1295.493.3
RefPAC-Sreference-based=true2023.0394.993.7
RefPAC-SReference-based=true, Backbone=ViT-B/322025.1294.993.7
BLIP2ScoreReference-based=false2025.1294.394.3
CIDErreference-based=true2023.0394.185.7
RefPAC-S++Reference-based=true, Backbone=ViT-B/322025.1294.193.5
CLAIRReference-based=true2025.1293.6—
MIDreference-based=true2023.0393.590.5
HICEScoreReference-based=false2025.1293.193.1
RefCLIP-Sreference-based=true2023.0392.691
RefCLIP-SReference-based=true, Backbone=ViT-B/322025.1292.691
CIDErReference-based=true2025.1290.682.5
PAC-S++Reference-based=false, Backbone=ViT-B/322025.1290.290.2
PAC-Sreference-based=false2023.0389.989.9
PAC-SReference-based=false, Backbone=ViT-B/322025.1289.989.9
CLIP-Sreference-based=false2023.0387.287.2
CLIP-SReference-based=false2025.1287.287.2
BLEU-4reference-based=true2023.038766.2
SPICEReference-based=true2025.1286.175.5
BLEU-1reference-based=true2023.0385.465.7
BLEUReference-based=true2025.1282.666.5
METEORReference-based=true2025.1282.678.8
METEORreference-based=true2023.038270.1
ROUGEReference-based=true2025.1279.371.7
ROUGEreference-based=true2023.0370.454.6