Retrieval-Augmented Generation on Average (5 RAG Datasets)
76.3FaithfulnessHyTE-Hbert
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| HyTE-HbertRetrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 76.3 | 90.4 | 83.2 | |
| GTERetrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 65.9 | 70.1 | 65 | |
| KaLM-mini-v1Retrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 62.4 | 71.9 | 59.1 | |
| ModernBert*Retrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 61.7 | 74.8 | 63.2 | |
| GemmaRetrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 60.3 | 73.5 | 68.4 |