Opinion Alignment on WGM
89.8Opinion AlignmentLlama-3.2-90B
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-3.2-90BPrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 89.8 | |
| Mistral-largePrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 89.4 | |
| Qwen-2.5-72BPrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 89.4 | |
| Claude-3.5-v2Prompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 89.3 | |
| Claude-3.5-v2Prompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 89.3 | |
| Qwen-2.5-72BPrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 89.1 | |
| Claude-3.5-v2Prompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 89 | |
| Llama-3.2-90BPrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 89 | |
| Mistral-largePrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 88.9 | |
| Mistral-largePrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 88.4 | |
| Qwen-2.5-72BPrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 88.2 | |
| Claude-3.5-v2Prompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 87.7 | |
| Mistral-largePrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 87.3 | |
| Qwen-2.5-72BPrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 87.1 | |
| Llama-3.2-90BPrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 86.2 | |
| Llama-3.2-90BPrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 86.1 | |
| Llama-3.2-90BPrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 86 | |
| Claude-3.5-v2Prompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 85.2 | |
| Qwen-2.5-72BPrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 85.2 | |
| Claude-3.5-v2Prompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 85.1 | |
| OLMo-2-7B-IPrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 85.1 | |
| Llama-3.2-90BPrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 85 | |
| Mistral-largePrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 84.9 | |
| Llama-3.2-90BPrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 84.8 | |
| Mistral-largePrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 84.7 | |
| Mistral-largePrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 84.7 | |
| Llama-3.2-90BPrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 84.6 | |
| OLMo-2-7B-IPrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Calibrated2025.07 | 84.6 | |
| Claude-3.5-v2Prompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 84.4 | |
| Claude-3.5-v2Prompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 84.2 | |
| Qwen-2.5-72BPrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 84.1 | |
| Mistral-largePrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 83.9 | |
| Qwen-2.5-72BPrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 83.2 | |
| Qwen-2.5-72BPrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 83.1 | |
| OLMo-2-7B-IPrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 82.7 | |
| OLMo-2-7B-IPrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 82.5 | |
| OLMo-2-7B-IPrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Calibrated2025.07 | 81.5 | |
| OLMo-2-7B-IPrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Calibrated2025.07 | 80.4 | |
| Llama-3.2-90BPrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 73 | |
| Mistral-largePrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 72 | |
| Llama-3.2-90BPrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 70.6 | |
| OLMo-2-7B-IPrompt Type=Sociodemographic prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 69.8 | |
| Mistral-largePrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 68.4 | |
| Llama-3.2-90BPrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 68.1 | |
| OLMo-2-7B-IPrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 67.7 | |
| Llama-3.2-90BPrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 67.6 | |
| Claude-3.5-v2Prompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 66.2 | |
| Qwen-2.5-72BPrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 66 | |
| Claude-3.5-v2Prompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 65.4 | |
| OLMo-2-7B-IPrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 64.5 | |
| Qwen-2.5-72BPrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 63.4 | |
| Mistral-largePrompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 63 | |
| Mistral-largePrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 62.4 | |
| OLMo-2-7B-IPrompt Type=Sociodemographic prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 62.3 | |
| Claude-3.5-v2Prompt Type=Sociodemographic prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 61.4 | |
| OLMo-2-7B-IPrompt Type=Base prompt, Elicitation Method=Verbalized, Calibration Status=Original2025.07 | 59.8 | |
| OLMo-2-7B-IPrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 59.6 | |
| Claude-3.5-v2Prompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 59.5 | |
| Qwen-2.5-72BPrompt Type=Base prompt, Elicitation Method=Paraphrase, Calibration Status=Original2025.07 | 57.7 | |
| Qwen-2.5-72BPrompt Type=Base prompt, Elicitation Method=Self-random, Calibration Status=Original2025.07 | 53.3 |