Question Answering on ConflictQA-TextConf complementary setting 1.0 (test)
89.82F1 (Positive)Deepseek-V3.2-Thinking
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Deepseek-V3.2-ThinkingModel Category=Reasoning LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 89.82 | 56.34 | 33.4837 | 81.86 | 39.3 | 42.5652 | |
| GPT-5.1Model Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 89.26 | 69.18 | 20.0823 | 82.79 | 55.58 | 27.2133 | |
| Qwen3-8BModel Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 88.99 | 68.73 | 20.2623 | 78.63 | 46.98 | 31.654 | |
| GPT-4oModel Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 87.62 | 61.1 | 26.523 | 80 | 44.42 | 35.5844 | |
| GPT-3.5-Turbo-0125Model Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 85.55 | 59.23 | 26.3231 | 78.6 | 41.4 | 37.2047 | |
| Qwen3-30B-A3B-ThinkingModel Category=Reasoning LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 84.28 | 55.35 | 28.9334 | 76.51 | 44.42 | 32.0942 | |
| o3-miniModel Category=Reasoning LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 83.7 | 60 | 23.7028 | 74.65 | 48.6 | 26.0535 | |
| Deepseek-V3.2Model Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 83.56 | 61.08 | 22.4827 | 74.19 | 51.86 | 22.333 | |
| Llama-3.1-70B-InstructModel Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 83 | 47.46 | 35.5443 | 74.65 | 33.72 | 40.9355 | |
| Mistral-Large-2512Model Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 82.12 | 52 | 30.1237 | 72.09 | 28.84 | 43.256 | |
| Llama-3.1-8B-InstructModel Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 80.39 | 42.56 | 37.8347 | 64.19 | 21.63 | 42.5666 | |
| Open-Mistral-7BModel Category=General LLM, Protocol=Zero-shot, Prompting=Conflict-aware QA prompt2026.04 | 73.98 | 51.81 | 22.173 | 59.3 | 38.14 | 21.1636 |