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

Open-book generation under knowledge conflict on ConFiQA MR 1,500

59.8Ps Score

ContextDPO

28.111236.338144.56552.7919Jan 7, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
59.820.6725.68
2026.01
57.5321.3327.05
2026.01
57.3321.4727.24
2026.01
54.4716.0722.78
2026.01
51.421.2729.27
2026.01
48.9314.8723.3
2026.01
4522.3333.17
2026.01
42.224.436.64
2026.01
4223.6736.04
2026.01
41.9324.6737.04
2026.01
40.472437.22
2026.01
36.8724.439.83
2026.01
34.072945.98
2026.01
32.8729.647.39
2026.01
30.232.451.76
2026.01
29.3327.8748.72