Reading Comprehension on MultiRC
88.2F1 ScorePaLM 2-L
Evaluation Results
| Method | Links | |
|---|---|---|
| PaLM 2-Lprompting=1-shot2023.05 | 88.2 | |
| PaLMprompting=1-shot2023.05 | 84.9 | |
| PaLM 2-Mprompting=1-shot2023.05 | 84.1 | |
| PaLM 2-Sprompting=1-shot2023.05 | 84 | |
| RandomBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 60.4 | |
| BM25Backbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 58.7 | |
| ConMeZOModel=OPT-13B2025.11 | 58.3 | |
| MeZOModel=OPT-13B2025.11 | 57.53 | |
| Zero-shotBackbone=LLaMA-7B, Evaluation Setting=Zero-shot2025.05 | 57 | |
| GENICLBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 56.9 | |
| MeZOModel=OPT-1.3B2025.11 | 55.9 | |
| E5baseBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 54 | |
| ConMeZOModel=OPT-1.3B2025.11 | 53.5 | |
| SBERTBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 53.3 | |
| EPRBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 50.4 | |
| LLM-RBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 50.2 | |
| CBDSBackbone=LLaMA-7B, Evaluation Setting=Few-shot (ICL)2025.05 | 49.3 |