Hallucination Detection on FELM
48.3F1 Scoregpt4-0314
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| gpt4-03142026.05 | 48.3 | 67.1 | |
| DSEmbedding Model=Qwen32026.05 | 44.8 | 67.7 | |
| DSEmbedding Model=Mistral2026.05 | 44.7 | 67 | |
| DSEmbedding Model=Llama-32026.05 | 43 | 68.4 | |
| DSEmbedding Model=F2LLM2026.05 | 41.4 | 65.4 | |
| DSEmbedding Model=Jina-v52026.05 | 39.3 | 63.5 | |
| Vicuna-33B2026.05 | 32.5 | 56.5 | |
| gpt3.5-03012026.05 | 25.5 | 55.9 |