List your company

Claim Verification on 9-dataset aggregate retrieval-free setting (test)

84ROC-AUCGPT-4.1
47.18456.74266.375.858Mar 5, 2026

Evaluation results

MethodLinks
GPT-4.1Retrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.038478.3
Verb+RAGRetrieval setting=Retrieval-Based, Backbone=Ministral2026.0378.269.6
Verb+RAGRetrieval setting=Retrieval-Based, Backbone=Llama 3.12026.0377.770.1
INTRARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0377.773.1
Verb+RAGRetrieval setting=Retrieval-Based, Backbone=Avg2026.0377.568.9
Verb+RAGRetrieval setting=Retrieval-Based, Backbone=Phi-42026.0376.567.1
SheepsRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.037570.5
VerbRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0374.768.4
MMRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0373.368.7
INTRARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.0373.369
CCSRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0373.168.9
INTRARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0372.869.3
VerbRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0372.266.5
VerbRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.037264.5
SheepsRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.037267.6
SheepsRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0371.667.6
MMRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0371.468.3
CCSRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0371.164.1
SPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0370.966.9
MINDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0370.667
SAPLMARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0370.266.1
MINDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.037065.4
CCPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0369.867.6
SATRMDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0369.665.5
INTRARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0369.564.6
SheepsRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0369.464.6
VerbRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0369.164.5
MINDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.0369.165.6
SPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.036964.9
SPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0368.864.9
PPLRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0368.665.6
SAPLMARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0368.464.5
SAPLMARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.036864.4
MMRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.0367.864.7
PPLRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0367.564.3
PPLRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0367.364.2
CCPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0367.165.5
MINDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0366.864.4
PPLRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0366.663.1
SATRMDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.0366.663.1
SPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0366.462.8
CCSRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.0365.761.6
TADRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0365.762.4
SAPLMARetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0365.462.6
SATRMDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0365.362.5
SATRMDRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0364.961.2
TADRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Phi-42026.0364.761.2
TADRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Avg2026.0364.761.5
RAUQRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0363.961.1
RAUQRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0363.860.7
TADRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0363.860.9
FocusRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0363.660.6
RAUQRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0363.160.2
UHeadRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Llama 3.12026.0363.160.2
MTERetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.0362.559
CCPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0361.960.8
FocusRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0361.958.9
RAUQRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0361.658.6
MTERetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0361.457.9
MTERetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0360.958
MTERetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0360.856.6
MMRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.0358.757.1
FocusRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0358.658.2
CCSRetrieval setting=Retrieval-Free, Supervision level=Supervised, Backbone=Ministral2026.035351.8
Att. ScoreRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Ministral2026.0351.151
Att. ScoreRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Avg2026.0350.550.6
Att. ScoreRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0350.350.6
FocusRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0350.255.1
Att. ScoreRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Llama 3.12026.035050.2
CCPRetrieval setting=Retrieval-Free, Supervision level=Unsupervised, Backbone=Phi-42026.0348.649.2