Semantic Parsing on NL2Bash
45.19AccuracyCLG
Evaluation Results
| Method | Links | |
|---|---|---|
| CLGModel=Qwen2.5-72B, Shots=1282025.06 | 45.19 | |
| BGE-KMeansModel=Qwen2.5-72B, Shots=1282025.06 | 40.86 | |
| BM25-MajorModel=Qwen2.5-72B, Shots=1282025.06 | 38.11 | |
| Latent-BayesianModel=Qwen2.5-72B, Shots=1282025.06 | 37.36 | |
| Best-of-NModel=Qwen2.5-72B, Shots=1282025.06 | 37.13 | |
| RandomModel=Qwen2.5-72B, Shots=1282025.06 | 33.28 | |
| Best-of-NModel=Llama3-70B, Shots=1282025.06 | 29.76 | |
| RandomModel=Llama3-70B, Shots=1282025.06 | 29.72 | |
| CLGModel=Llama3-70B, Shots=1282025.06 | 29.59 | |
| Latent-BayesianModel=Llama3-70B, Shots=1282025.06 | 29.2 | |
| BGE-KMeansModel=Llama3-70B, Shots=1282025.06 | 28.39 | |
| BM25-MajorModel=Llama3-70B, Shots=1282025.06 | 27.92 | |
| EPR-KMeansModel=Qwen2.5-72B, Shots=1282025.06 | 26.53 | |
| EPR-KMeansModel=Llama3-70B, Shots=1282025.06 | 22.92 |