Hallucination Detection on Summ
81.5ROC-AUCRAUQ
Evaluation results
| Method | Links | |
|---|---|---|
| RAUQLLM Model=Llama-3.1 8B2025.05 | 81.5 | |
| PerplexityLLM Model=Llama-3.1 8B2025.05 | 81.2 | |
| RAUQLLM Model=Gemma-2 9B2025.05 | 77.2 | |
| PerplexityLLM Model=Gemma-2 9B2025.05 | 76.6 | |
| FocusLLM Model=Llama-3.1 8B2025.05 | 74.6 | |
| FocusLLM Model=Gemma-2 9B2025.05 | 73.8 | |
| MSPLLM Model=Gemma-2 9B2025.05 | 73.5 | |
| CCPLLM Model=Gemma-2 9B2025.05 | 73.1 | |
| Simple FocusLLM Model=Llama-3.1 8B2025.05 | 73 | |
| Simple FocusLLM Model=Gemma-2 9B2025.05 | 72.3 | |
| MSPLLM Model=Llama-3.1 8B2025.05 | 71.8 | |
| CCPLLM Model=Llama-3.1 8B2025.05 | 70.5 | |
| SARLLM Model=Gemma-2 9B2025.05 | 67 | |
| PerplexityLLM Model=Qwen-2.5 7B2025.05 | 66.1 | |
| LUQLLM Model=Gemma-2 9B2025.05 | 64.4 | |
| LUQLLM Model=Llama-3.1 8B2025.05 | 63.3 | |
| RAUQLLM Model=Qwen-2.5 7B2025.05 | 62.9 | |
| SARLLM Model=Llama-3.1 8B2025.05 | 62.7 | |
| LUQLLM Model=Qwen-2.5 7B2025.05 | 62.7 | |
| Lexical Similarity Rouge-LLLM Model=Gemma-2 9B2025.05 | 62 | |
| FocusLLM Model=Qwen-2.5 7B2025.05 | 61.2 | |
| DegMat NLI Score entail.LLM Model=Gemma-2 9B2025.05 | 61.2 | |
| Semantic DensityLLM Model=Gemma-2 9B2025.05 | 61.1 | |
| EVL NLI Score entail.LLM Model=Gemma-2 9B2025.05 | 60.7 | |
| PerplexityLLM Model=Falcon-3 10B2025.05 | 60.6 | |
| Lexical Similarity Rouge-LLLM Model=Llama-3.1 8B2025.05 | 60.5 | |
| DegMat NLI Score entail.LLM Model=Qwen-2.5 7B2025.05 | 60.4 | |
| EVL NLI Score entail.LLM Model=Qwen-2.5 7B2025.05 | 60.2 | |
| RAUQLLM Model=Falcon-3 10B2025.05 | 59.7 | |
| Semantic EntropyLLM Model=Gemma-2 9B2025.05 | 59.5 | |
| Lexical Similarity Rouge-LLLM Model=Qwen-2.5 7B2025.05 | 59.4 | |
| EigenScoreLLM Model=Gemma-2 9B2025.05 | 59.2 | |
| DegMat NLI Score entail.LLM Model=Llama-3.1 8B2025.05 | 59.1 | |
| EVL NLI Score entail.LLM Model=Llama-3.1 8B2025.05 | 59 | |
| SARLLM Model=Qwen-2.5 7B2025.05 | 59 | |
| Attention ScoreLLM Model=Falcon-3 10B2025.05 | 59 | |
| Simple FocusLLM Model=Qwen-2.5 7B2025.05 | 58.8 | |
| Semantic EntropyLLM Model=Llama-3.1 8B2025.05 | 58.3 | |
| MSPLLM Model=Falcon-3 10B2025.05 | 58.3 | |
| EVL NLI Score entail.LLM Model=Falcon-3 10B2025.05 | 58.3 | |
| Semantic DensityLLM Model=Falcon-3 10B2025.05 | 58.3 | |
| Semantic DensityLLM Model=Llama-3.1 8B2025.05 | 58.2 | |
| DegMat NLI Score entail.LLM Model=Falcon-3 10B2025.05 | 58.1 | |
| Semantic EntropyLLM Model=Falcon-3 10B2025.05 | 57.9 | |
| FocusLLM Model=Falcon-3 10B2025.05 | 57.7 | |
| CCPLLM Model=Qwen-2.5 7B2025.05 | 57.5 | |
| Semantic DensityLLM Model=Qwen-2.5 7B2025.05 | 57.2 | |
| LUQLLM Model=Falcon-3 10B2025.05 | 57 | |
| CCPLLM Model=Falcon-3 10B2025.05 | 56.9 | |
| SARLLM Model=Falcon-3 10B2025.05 | 56.9 | |
| MSPLLM Model=Qwen-2.5 7B2025.05 | 55.9 | |
| Lexical Similarity Rouge-LLLM Model=Falcon-3 10B2025.05 | 55.9 | |
| Attention ScoreLLM Model=Llama-3.1 8B2025.05 | 55.2 | |
| EigenScoreLLM Model=Qwen-2.5 7B2025.05 | 54.9 | |
| Ecc. NLI Score entail.LLM Model=Falcon-3 10B2025.05 | 54.6 | |
| Semantic EntropyLLM Model=Qwen-2.5 7B2025.05 | 54.4 | |
| Simple FocusLLM Model=Falcon-3 10B2025.05 | 54.3 | |
| Attention ScoreLLM Model=Gemma-2 9B2025.05 | 53.6 | |
| Ecc. NLI Score entail.LLM Model=Gemma-2 9B2025.05 | 53.5 | |
| EigenScoreLLM Model=Llama-3.1 8B2025.05 | 53.3 | |
| Attention ScoreLLM Model=Qwen-2.5 7B2025.05 | 53 | |
| EigenScoreLLM Model=Falcon-3 10B2025.05 | 52.7 | |
| Ecc. NLI Score entail.LLM Model=Qwen-2.5 7B2025.05 | 51 | |
| Ecc. NLI Score entail.LLM Model=Llama-3.1 8B2025.05 | 49.8 |