Question Answering on QA (Mean PRR)
42.5Mean PRRRAUQ
Evaluation Results
| Method | Links | |
|---|---|---|
| RAUQLLM Backbone=SmolLM-2 360M2025.05 | 42.5 | |
| RAUQBase LLM=Gemma-2 9B2025.05 | 42.1 | |
| FocusBase LLM=Gemma-2 9B2025.05 | 41.6 | |
| Simple FocusLLM Backbone=SmolLM-2 360M2025.05 | 40.1 | |
| Simple FocusBase LLM=Gemma-2 9B2025.05 | 39.6 | |
| RAUQBase LLM=Llama-3.1 8B2025.05 | 39.6 | |
| RAUQBase LLM=Falcon-3 10B2025.05 | 39.2 | |
| Semantic DensityLLM Backbone=Llama-3.1 70B2025.05 | 38.5 | |
| PerplexityBase LLM=Gemma-2 9B2025.05 | 38.3 | |
| SARLLM Backbone=Llama-3.1 70B2025.05 | 38.2 | |
| Simple FocusLLM Backbone=Llama-3.1 70B2025.05 | 38 | |
| DegMat NLI Score entail.LLM Backbone=Llama-3.1 70B2025.05 | 38 | |
| LUQLLM Backbone=Llama-3.1 70B2025.05 | 37.6 | |
| Semantic DensityBase LLM=Gemma-2 9B2025.05 | 37.5 | |
| PerplexityLLM Backbone=SmolLM-2 360M2025.05 | 37.1 | |
| Simple FocusLLM Backbone=Llama-3.2 1B2025.05 | 37 | |
| EVL NLI Score entail.LLM Backbone=Llama-3.1 70B2025.05 | 36.9 | |
| MSPLLM Backbone=Llama-3.1 70B2025.05 | 36.4 | |
| Lexical Similarity Rouge-LLLM Backbone=Llama-3.1 70B2025.05 | 36.2 | |
| MSPBase LLM=Gemma-2 9B2025.05 | 36.1 | |
| SARBase LLM=Gemma-2 9B2025.05 | 36.1 | |
| MSPLLM Backbone=SmolLM-2 360M2025.05 | 36 | |
| RAUQLLM Backbone=Llama-3.1 70B2025.05 | 36 | |
| Semantic DensityBase LLM=Falcon-3 10B2025.05 | 35.8 | |
| RAUQBase LLM=Qwen-2.5 7B2025.05 | 35.8 | |
| Semantic DensityLLM Backbone=SmolLM-2 360M2025.05 | 35.7 | |
| PerplexityBase LLM=Falcon-3 10B2025.05 | 35.6 | |
| DegMat NLI Score entail.Base LLM=Qwen-2.5 7B2025.05 | 35.6 | |
| RAUQLLM Backbone=Llama-3.2 1B2025.05 | 35.6 | |
| DegMat NLI Score entail.Base LLM=Falcon-3 10B2025.05 | 35.2 | |
| Semantic DensityBase LLM=Qwen-2.5 7B2025.05 | 35.2 | |
| Simple FocusBase LLM=Falcon-3 10B2025.05 | 35.1 | |
| EVL NLI Score entail.Base LLM=Falcon-3 10B2025.05 | 35.1 | |
| LUQBase LLM=Qwen-2.5 7B2025.05 | 35.1 | |
| SARBase LLM=Qwen-2.5 7B2025.05 | 35.1 | |
| CCPLLM Backbone=Llama-3.1 70B2025.05 | 35 | |
| EVL NLI Score entail.Base LLM=Qwen-2.5 7B2025.05 | 34.9 | |
| Semantic DensityLLM Backbone=Llama-3.2 1B2025.05 | 34.8 | |
| MSPBase LLM=Llama-3.1 8B2025.05 | 34.7 | |
| PerplexityBase LLM=Llama-3.1 8B2025.05 | 34.7 | |
| MSPBase LLM=Falcon-3 10B2025.05 | 34.5 | |
| LUQBase LLM=Gemma-2 9B2025.05 | 34.4 | |
| PerplexityBase LLM=Qwen-2.5 7B2025.05 | 34.3 | |
| SARLLM Backbone=SmolLM-2 360M2025.05 | 34.3 | |
| Simple FocusBase LLM=Llama-3.1 8B2025.05 | 34.2 | |
| Simple FocusBase LLM=Qwen-2.5 7B2025.05 | 34.2 | |
| DegMat NLI Score entail.LLM Backbone=SmolLM-2 360M2025.05 | 34.2 | |
| DegMat NLI Score entail.Base LLM=Gemma-2 9B2025.05 | 33.7 | |
| LUQLLM Backbone=SmolLM-2 360M2025.05 | 33.7 | |
| LUQBase LLM=Falcon-3 10B2025.05 | 33.5 | |
| Lexical Similarity Rouge-LBase LLM=Qwen-2.5 7B2025.05 | 33.4 | |
| SARBase LLM=Falcon-3 10B2025.05 | 33.4 | |
| EVL NLI Score entail.LLM Backbone=SmolLM-2 360M2025.05 | 33.3 | |
| EVL NLI Score entail.Base LLM=Gemma-2 9B2025.05 | 33.2 | |
| Semantic DensityBase LLM=Llama-3.1 8B2025.05 | 33 | |
| Ecc. NLI Score entail.LLM Backbone=Llama-3.1 70B2025.05 | 33 | |
| MSPBase LLM=Qwen-2.5 7B2025.05 | 32.9 | |
| CCPBase LLM=Gemma-2 9B2025.05 | 32.9 | |
| Ecc. NLI Score entail.Base LLM=Falcon-3 10B2025.05 | 32.7 | |
| MSPLLM Backbone=Llama-3.2 1B2025.05 | 32.4 | |
| PerplexityLLM Backbone=Llama-3.1 70B2025.05 | 32.3 | |
| Ecc. NLI Score entail.Base LLM=Qwen-2.5 7B2025.05 | 32.2 | |
| FocusBase LLM=Llama-3.1 8B2025.05 | 32 | |
| Semantic EntropyBase LLM=Falcon-3 10B2025.05 | 32 | |
| FocusBase LLM=Falcon-3 10B2025.05 | 31.3 | |
| SARBase LLM=Llama-3.1 8B2025.05 | 31 | |
| PerplexityLLM Backbone=Llama-3.2 1B2025.05 | 31 | |
| Semantic EntropyLLM Backbone=Llama-3.1 70B2025.05 | 30.9 | |
| DegMat NLI Score entail.Base LLM=Llama-3.1 8B2025.05 | 30.6 | |
| Lexical Similarity Rouge-LBase LLM=Gemma-2 9B2025.05 | 30.6 | |
| DegMat NLI Score entail.LLM Backbone=Llama-3.2 1B2025.05 | 30.5 | |
| CCPBase LLM=Falcon-3 10B2025.05 | 29.9 | |
| Ecc. NLI Score entail.Base LLM=Gemma-2 9B2025.05 | 29.8 | |
| EigenScoreBase LLM=Qwen-2.5 7B2025.05 | 29.8 | |
| EVL NLI Score entail.LLM Backbone=Llama-3.2 1B2025.05 | 29.8 | |
| EigenScoreLLM Backbone=Llama-3.1 70B2025.05 | 29.6 | |
| SARLLM Backbone=Llama-3.2 1B2025.05 | 29.5 | |
| EVL NLI Score entail.Base LLM=Llama-3.1 8B2025.05 | 29.3 | |
| Semantic EntropyBase LLM=Gemma-2 9B2025.05 | 29.1 | |
| Lexical Similarity Rouge-LLLM Backbone=SmolLM-2 360M2025.05 | 29 | |
| LUQBase LLM=Llama-3.1 8B2025.05 | 28.7 | |
| CCPBase LLM=Llama-3.1 8B2025.05 | 28.5 | |
| Lexical Similarity Rouge-LBase LLM=Falcon-3 10B2025.05 | 28.5 | |
| CCPLLM Backbone=Llama-3.2 1B2025.05 | 28.3 | |
| Semantic EntropyBase LLM=Qwen-2.5 7B2025.05 | 28.1 | |
| CCPLLM Backbone=SmolLM-2 360M2025.05 | 28.1 | |
| LUQLLM Backbone=Llama-3.2 1B2025.05 | 27.9 | |
| Ecc. NLI Score entail.Base LLM=Llama-3.1 8B2025.05 | 27.4 | |
| CCPBase LLM=Qwen-2.5 7B2025.05 | 27.1 | |
| EigenScoreBase LLM=Gemma-2 9B2025.05 | 26.7 | |
| FocusBase LLM=Qwen-2.5 7B2025.05 | 26.4 | |
| Lexical Similarity Rouge-LLLM Backbone=Llama-3.2 1B2025.05 | 25.5 | |
| Semantic EntropyBase LLM=Llama-3.1 8B2025.05 | 25.4 | |
| Lexical Similarity Rouge-LBase LLM=Llama-3.1 8B2025.05 | 25 | |
| EigenScoreBase LLM=Falcon-3 10B2025.05 | 24.7 | |
| EigenScoreBase LLM=Llama-3.1 8B2025.05 | 23.2 | |
| Ecc. NLI Score entail.LLM Backbone=Llama-3.2 1B2025.05 | 22.5 | |
| Ecc. NLI Score entail.LLM Backbone=SmolLM-2 360M2025.05 | 20.9 | |
| Semantic EntropyLLM Backbone=SmolLM-2 360M2025.05 | 20.1 | |
| Semantic EntropyLLM Backbone=Llama-3.2 1B2025.05 | 18.7 |