List your company

Explanation Refinement on FOLIO

85.25Initial ScoreLLM-TP Tree
43.473254.319165.16576.0109Jan 27, 2026

Evaluation results

MethodLinks
LLM-TP TreeBackbone=Qwen3-max2026.0185.2595.08
LLM-TP TreeBackbone=Deepseek-V3.12026.0183.6192.62
LLM-TP TreeBackbone=GPT-4o2026.0181.1590.16
Faithful-RefinerBackbone=Deepseek-V3.12026.0171.3181.15
Faithful-RefinerBackbone=Qwen3-max2026.0169.6784.43
Faithful-RefinerBackbone=GPT-4o2026.0168.0378.69
LLM-TP TreeBackbone=GPT-5 nano2026.0166.3981.15
LLM-TP TreeBackbone=Grok-4 fast2026.0162.379.51
Explanation-RefinerBackbone=Qwen3-max2026.0155.7468.85
Faithful-RefinerBackbone=Grok-4 fast2026.0154.9265.57
Explanation-RefinerBackbone=GPT-4o2026.0153.2863.93
Faithful-RefinerBackbone=GPT-5 nano2026.0153.2868.03
Explanation-RefinerBackbone=Deepseek-V3.12026.0150.8262.3
Explanation-RefinerBackbone=GPT-5 nano2026.0146.7259.84
Explanation-RefinerBackbone=Grok-4 fast2026.0145.0852.46