Summarization on TriviaQA (Memorization)
52F1 Score (TriviaQA Mem)Chain of Summaries (CoS)
Evaluation Results
| Method | Links | |
|---|---|---|
| Chain of Summaries (CoS)Backbone=Qwen2.5:7B2025.11 | 52 | |
| Chain of Summaries (CoS)Backbone=GPT-4o-mini2025.11 | 48 | |
| Zero-shot summaryBackbone=GPT-4o-mini2025.11 | 43 | |
| Chain of Summaries (CoS)Backbone=Llama3.2:3B2025.11 | 39 | |
| Zero-shot summaryBackbone=Qwen2.5:7B2025.11 | 23 | |
| Zero-shot summaryBackbone=Llama3.2:3B2025.11 | 21 |