Summarization on GovReport LongBench (test)
30.91ROUGE-1 ScoreQwen2.5-7B-Instruct
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Qwen2.5-7B-Instructsetting=zero-shot2026.02 | 30.91 | 11.68 | 15.2 | 19.26 | |
| MemAgent-7Bsetting=zero-shot2026.02 | 30.28 | 12.37 | 15.37 | 19.34 | |
| LycheeMemory-7Bsetting=zero-shot2026.02 | 30.12 | 13.08 | 15.07 | 19.42 |