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

Multi-hop QA on MuSiQue (Violation Metrics)

0.83Avg Violation

SAVER

0.73321.38662.042.6934Apr 9, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.04
0.8369.380.1119.73
2026.04
2.1626.17-36.51
2026.04
2.9113.26-37.58
2026.04
3.255.34-62.63