Question Answering on NQ-Open (ROUGE-Lsum)
0.2766ROUGE-LsumBase Model
Evaluation results
| Method | Links | |
|---|---|---|
| Base ModelLLM Backbone=Llama3B-Instruct, TTA Steps=0, TTA Method=None2026.02 | 0.2766 | |
| Naive TTALLM Backbone=Llama3B-Instruct, TTA Steps=1, TTA Method=Fixed2026.02 | 0.2722 | |
| SCALENET (Step-wise)LLM Backbone=Llama3B-Instruct, TTA Steps=5, TTA Method=Step-wise2026.02 | 0.2674 | |
| SCALENET (Step-wise)LLM Backbone=Llama3B-Instruct, TTA Steps=1, TTA Method=Step-wise2026.02 | 0.2662 | |
| SCALENET (Layer-wise)LLM Backbone=Llama3B-Instruct, TTA Steps=5, TTA Method=Layer-wise2026.02 | 0.2507 | |
| SCALENET (Layer-wise)LLM Backbone=Llama3B-Instruct, TTA Steps=1, TTA Method=Layer-wise2026.02 | 0.2398 | |
| SCALENET (Layer-wise)LLM Backbone=Qwen4B-Instruct, TTA Steps=5, TTA Method=Layer-wise2026.02 | 0.1706 | |
| SCALENET (Layer-wise)LLM Backbone=Qwen4B-Instruct, TTA Steps=1, TTA Method=Layer-wise2026.02 | 0.1513 | |
| Naive TTALLM Backbone=Qwen4B-Instruct, TTA Steps=5, TTA Method=Fixed2026.02 | 0.1495 | |
| Naive TTALLM Backbone=Qwen4B-Instruct, TTA Steps=1, TTA Method=Fixed2026.02 | 0.1424 | |
| Base ModelLLM Backbone=Qwen4B-Instruct, TTA Steps=0, TTA Method=None2026.02 | 0.132 | |
| SCALENET (Step-wise)LLM Backbone=Qwen4B-Instruct, TTA Steps=5, TTA Method=Step-wise2026.02 | 0.1041 | |
| SCALENET (Step-wise)LLM Backbone=Qwen4B-Instruct, TTA Steps=1, TTA Method=Step-wise2026.02 | 0.0866 | |
| Naive TTALLM Backbone=Llama3B-Instruct, TTA Steps=5, TTA Method=Fixed2026.02 | 0.0288 |