| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | HQA | EM0.442 | 55 | |
| Information Retrieval | HQA | NDCG@10 (Dense)69.6 | 21 | |
| Private information retention | HQA D_special (test) | r_pri27.67 | 20 | |
| Knowledge gap detection | HQA | Accuracy81.5 | 18 | |
| Knowledge-Intensive Reasoning | HQA | Average Score87 | 18 | |
| Question Answering | HQA (val) | EM35.2 | 14 | |
| Question Answering | HQA (in-domain) | EM39.6 | 14 | |
| Question Answering | HQA (test) | Accuracy26.9 | 11 | |
| De-Anonymization Resistance | HQA (test) | r_connect0.4407 | 10 | |
| Public Information Retention | HQA D_special (test) | r_pub47.2 | 10 | |
| Information Retrieval | HQA (test) | Recall@557.7 | 7 | |
| Context Compression & QA | HQA (val) | EM30.4 | 6 |