Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Fact Checking on LIAR (Acc@1, Avg. Perf.)

69Accuracy@1

DisambiguSLM

47.78453.29258.864.308Apr 25, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
6968.6
2026.04
67.666.6
2026.04
67.166.9
2026.04
66.666.3
2026.04
65.964.8
2026.04
65.966
2026.04
65.763.9
2026.04
65.463.8
2026.04
65.163.9
2026.04
64.764.8
2026.04
64.263.1
2026.04
64.165
2026.04
63.864
2026.04
63.561.6
2026.04
63.462.4
2026.04
63.264.5
2026.04
6361.6
2026.04
62.865
2026.04
62.661.7
2026.04
62.161.2
2026.04
6260.9
2026.04
61.962.7
2026.04
61.560.4
2026.04
61.262
2026.04
61.162.2
2026.04
60.859.2
2026.04
60.462.3
2026.04
60.361.4
2026.04
59.958.2
2026.04
59.761.4
2026.04
50.561.1
2026.04
49.258.8
2026.04
48.657.93