Summarization on Summ
0.517Mean PRRCCP
Evaluation Results
| Method | Links | |
|---|---|---|
| CCPLLM Backbone=Llama-3.2 1B2025.05 | 0.517 | |
| MSPLLM Backbone=Llama-3.2 1B2025.05 | 0.507 | |
| Simple FocusLLM Backbone=Llama-3.2 1B2025.05 | 0.488 | |
| CCPLLM Backbone=SmolLM-2 360M2025.05 | 0.457 | |
| MSPLLM Backbone=SmolLM-2 360M2025.05 | 0.449 | |
| Simple FocusLLM Backbone=SmolLM-2 360M2025.05 | 0.429 | |
| RAUQBase LLM=Llama-3.1 8B2025.05 | 0.428 | |
| RAUQLLM Backbone=Llama-3.2 1B2025.05 | 0.423 | |
| PerplexityBase LLM=Llama-3.1 8B2025.05 | 0.419 | |
| RAUQBase LLM=Gemma-2 9B2025.05 | 0.392 | |
| PerplexityLLM Backbone=Llama-3.2 1B2025.05 | 0.392 | |
| PerplexityBase LLM=Gemma-2 9B2025.05 | 0.375 | |
| RAUQLLM Backbone=SmolLM-2 360M2025.05 | 0.356 | |
| CCPBase LLM=Gemma-2 9B2025.05 | 0.345 | |
| FocusBase LLM=Gemma-2 9B2025.05 | 0.34 | |
| FocusBase LLM=Llama-3.1 8B2025.05 | 0.335 | |
| MSPBase LLM=Gemma-2 9B2025.05 | 0.334 | |
| PerplexityLLM Backbone=SmolLM-2 360M2025.05 | 0.33 | |
| Simple FocusBase LLM=Gemma-2 9B2025.05 | 0.322 | |
| CCPBase LLM=Llama-3.1 8B2025.05 | 0.307 | |
| Simple FocusBase LLM=Llama-3.1 8B2025.05 | 0.306 | |
| MSPBase LLM=Llama-3.1 8B2025.05 | 0.296 | |
| PerplexityBase LLM=Qwen-2.5 7B2025.05 | 0.254 | |
| PerplexityLLM Backbone=Llama-3.1 70B2025.05 | 0.245 | |
| RAUQLLM Backbone=Llama-3.1 70B2025.05 | 0.245 | |
| SARBase LLM=Gemma-2 9B2025.05 | 0.235 | |
| Semantic DensityLLM Backbone=Llama-3.2 1B2025.05 | 0.217 | |
| RAUQBase LLM=Qwen-2.5 7B2025.05 | 0.213 | |
| Semantic DensityLLM Backbone=SmolLM-2 360M2025.05 | 0.209 | |
| LUQBase LLM=Gemma-2 9B2025.05 | 0.206 | |
| LUQBase LLM=Qwen-2.5 7B2025.05 | 0.196 | |
| Attention ScoreBase LLM=Falcon-3 10B2025.05 | 0.192 | |
| CCPBase LLM=Qwen-2.5 7B2025.05 | 0.186 | |
| FocusBase LLM=Qwen-2.5 7B2025.05 | 0.186 | |
| RAUQBase LLM=Falcon-3 10B2025.05 | 0.181 | |
| PerplexityBase LLM=Falcon-3 10B2025.05 | 0.18 | |
| MSPBase LLM=Falcon-3 10B2025.05 | 0.177 | |
| LUQBase LLM=Llama-3.1 8B2025.05 | 0.173 | |
| SARBase LLM=Llama-3.1 8B2025.05 | 0.17 | |
| Semantic DensityBase LLM=Gemma-2 9B2025.05 | 0.167 | |
| Lexical Similarity Rouge-LBase LLM=Gemma-2 9B2025.05 | 0.161 | |
| DegMat NLI Score entail.Base LLM=Qwen-2.5 7B2025.05 | 0.154 | |
| EVL NLI Score entail.Base LLM=Qwen-2.5 7B2025.05 | 0.154 | |
| SARBase LLM=Qwen-2.5 7B2025.05 | 0.153 | |
| Semantic DensityBase LLM=Llama-3.1 8B2025.05 | 0.153 | |
| MSPBase LLM=Qwen-2.5 7B2025.05 | 0.151 | |
| Semantic DensityBase LLM=Falcon-3 10B2025.05 | 0.141 | |
| FocusBase LLM=Falcon-3 10B2025.05 | 0.139 | |
| LUQLLM Backbone=Llama-3.1 70B2025.05 | 0.139 | |
| DegMat NLI Score entail.Base LLM=Gemma-2 9B2025.05 | 0.138 | |
| Simple FocusBase LLM=Qwen-2.5 7B2025.05 | 0.136 | |
| EVL NLI Score entail.Base LLM=Falcon-3 10B2025.05 | 0.135 | |
| CCPLLM Backbone=Llama-3.1 70B2025.05 | 0.135 | |
| EVL NLI Score entail.Base LLM=Gemma-2 9B2025.05 | 0.133 | |
| Semantic EntropyBase LLM=Falcon-3 10B2025.05 | 0.133 | |
| DegMat NLI Score entail.Base LLM=Falcon-3 10B2025.05 | 0.132 | |
| Lexical Similarity Rouge-LBase LLM=Llama-3.1 8B2025.05 | 0.131 | |
| Lexical Similarity Rouge-LBase LLM=Qwen-2.5 7B2025.05 | 0.131 | |
| Attention ScoreBase LLM=Qwen-2.5 7B2025.05 | 0.13 | |
| CCPBase LLM=Falcon-3 10B2025.05 | 0.128 | |
| MSPLLM Backbone=Llama-3.1 70B2025.05 | 0.128 | |
| Simple FocusLLM Backbone=Llama-3.1 70B2025.05 | 0.128 | |
| Attention ScoreBase LLM=Llama-3.1 8B2025.05 | 0.126 | |
| Semantic EntropyBase LLM=Gemma-2 9B2025.05 | 0.126 | |
| LUQBase LLM=Falcon-3 10B2025.05 | 0.121 | |
| DegMat NLI Score entail.Base LLM=Llama-3.1 8B2025.05 | 0.118 | |
| LUQLLM Backbone=Llama-3.2 1B2025.05 | 0.118 | |
| Semantic EntropyBase LLM=Llama-3.1 8B2025.05 | 0.117 | |
| EVL NLI Score entail.Base LLM=Llama-3.1 8B2025.05 | 0.114 | |
| Semantic DensityBase LLM=Qwen-2.5 7B2025.05 | 0.11 | |
| EigenScoreBase LLM=Gemma-2 9B2025.05 | 0.106 | |
| SARLLM Backbone=Llama-3.1 70B2025.05 | 0.106 | |
| Attention ScoreBase LLM=Gemma-2 9B2025.05 | 0.103 | |
| Semantic DensityLLM Backbone=Llama-3.1 70B2025.05 | 0.1 | |
| Simple FocusBase LLM=Falcon-3 10B2025.05 | 0.095 | |
| SARLLM Backbone=SmolLM-2 360M2025.05 | 0.095 | |
| SARBase LLM=Falcon-3 10B2025.05 | 0.094 | |
| Semantic EntropyBase LLM=Qwen-2.5 7B2025.05 | 0.092 | |
| SARLLM Backbone=Llama-3.2 1B2025.05 | 0.091 | |
| DegMat NLI Score entail.LLM Backbone=Llama-3.1 70B2025.05 | 0.091 | |
| EVL NLI Score entail.LLM Backbone=Llama-3.1 70B2025.05 | 0.091 | |
| Lexical Similarity Rouge-LLLM Backbone=Llama-3.1 70B2025.05 | 0.089 | |
| Lexical Similarity Rouge-LBase LLM=Falcon-3 10B2025.05 | 0.084 | |
| Semantic EntropyLLM Backbone=Llama-3.2 1B2025.05 | 0.084 | |
| EigenScoreBase LLM=Llama-3.1 8B2025.05 | 0.078 | |
| DegMat NLI Score entail.LLM Backbone=Llama-3.2 1B2025.05 | 0.078 | |
| LUQLLM Backbone=SmolLM-2 360M2025.05 | 0.076 | |
| Lexical Similarity Rouge-LLLM Backbone=Llama-3.2 1B2025.05 | 0.074 | |
| EVL NLI Score entail.LLM Backbone=Llama-3.2 1B2025.05 | 0.072 | |
| Semantic EntropyLLM Backbone=Llama-3.1 70B2025.05 | 0.069 | |
| EigenScoreLLM Backbone=SmolLM-2 360M2025.05 | 0.068 | |
| Semantic EntropyLLM Backbone=SmolLM-2 360M2025.05 | 0.067 | |
| EigenScoreBase LLM=Qwen-2.5 7B2025.05 | 0.061 | |
| DegMat NLI Score entail.LLM Backbone=SmolLM-2 360M2025.05 | 0.059 | |
| EVL NLI Score entail.LLM Backbone=SmolLM-2 360M2025.05 | 0.055 | |
| EigenScoreBase LLM=Falcon-3 10B2025.05 | 0.051 | |
| Attention ScoreLLM Backbone=Llama-3.1 70B2025.05 | 0.045 | |
| EigenScoreLLM Backbone=Llama-3.1 70B2025.05 | 0.044 | |
| Ecc. NLI Score entail.Base LLM=Falcon-3 10B2025.05 | 0.038 | |
| Attention ScoreLLM Backbone=Llama-3.2 1B2025.05 | 0.033 |