Retrieval-Augmented Generation on ExpertQA
73.9FaithfulnessHyTE-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 | 73.9 | 95.8 | 83.4 | |
| GTERetrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 67.2 | 73.1 | 69.8 | |
| KaLM-mini-v1Retrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 60.7 | 66.6 | 52.2 | |
| ModernBert*Retrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 57.5 | 75.8 | 71.8 | |
| GemmaRetrieval Context Window Size=5, Generator Model=Llama-3.1-8B-Instruct, Judge Model=Llama-3.1-8B-Instruct2026.02 | 44.2 | 79.1 | 75.5 |