List your company

Tabular Question Answering on HiTab (val)

69.83Validation Reward (mean@4)ACPO
15.406829.535943.66557.7941Jun 21, 2026

Evaluation results

MethodLinks
ACPOBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0669.83
ACPOBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0669.83
CISPOBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0669.17
AR-LoptiBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0668.92
DAPOBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0668.42
Low-EntropyBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0667
ACPOBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0666.58
AR-LoptiBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0666.58
ACPOBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0666.58
DAPOBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0665.75
CISPOBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0665.67
Low-EntropyBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0665.08
High-EntropyBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0664.33
High-EntropyBackbone=Qwen2.5-7B, Policy Regime=OffP.2026.0661.83
ACPOBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0646.42
ACPOBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0646.42
ACPOBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0645.5
AR-LoptiBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0645.5
ACPOBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0645.5
High-EntropyBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0645
CISPOBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0644.83
DAPOBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0644.33
DAPOBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0644
CISPOBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0643.92
High-EntropyBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0643.5
AR-LoptiBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0643.33
Low-EntropyBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0643.17
Low-EntropyBackbone=Qwen2.5-3B, Policy Regime=OffP.2026.0643
Base ModelBackbone=Qwen2.5-7B, Policy Regime=N-OnP.2026.0631.25
Base ModelBackbone=Qwen2.5-7B2026.0631.25
Base ModelBackbone=Qwen2.5-3B, Policy Regime=N-OnP.2026.0617.5
Base ModelBackbone=Qwen2.5-3B2026.0617.5