Causal and Downstream Robustness Ablation Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Causal and Downstream Robustness Ablation Suite Averaged over 4 models
0.8Decoding Δ%
14
Causal and Downstream Robustness Ablation Suite
81Span F1
14
Causal and Downstream Robustness Ablation Suite Averaged over 4 models
4.1Tool Hit@1Δ
14
Causal and Downstream Robustness Ablation Suite Averaged over 4 models
3.7Fact EMΔ
14
Causal and Downstream Robustness Ablation Suite Averaged over LLaMA-3.1 70B, Phi-3 14B, GPT-J 6B, Qwen2.5 3B
86Causal Pass@5
14