Question Answering on AmbigQA (sampled)
65.5AccuracyPAGER
Evaluation Results
| Method | Links | |
|---|---|---|
| PAGERBackbone=GLM-4.5, Sample Size=2002026.01 | 65.5 | |
| Vanilla RAGBackbone=GLM-4.5, Sample Size=2002026.01 | 62.5 | |
| DeepNoteBackbone=GLM-4.5, Sample Size=2002026.01 | 55 | |
| Vanilla LLMBackbone=GLM-4.5, Sample Size=2002026.01 | 53 |