Summarization on TruthfulQA (Memorization)
46.06ROUGE-LChain of Summaries (CoS)
Evaluation Results
| Method | Links | |
|---|---|---|
| Chain of Summaries (CoS)Backbone=Qwen2.5:7B2025.11 | 46.06 | |
| Chain of Summaries (CoS)Backbone=GPT-4o-mini2025.11 | 30.34 | |
| Chain of Summaries (CoS)Backbone=Llama3.2:3B2025.11 | 29.31 | |
| Zero-shot summaryBackbone=GPT-4o-mini2025.11 | 24.04 | |
| Zero-shot summaryBackbone=Qwen2.5:7B2025.11 | 18.55 | |
| Zero-shot summaryBackbone=Llama3.2:3B2025.11 | 18.34 |