List your company

Summarization on TruthfulQA Generalization

14.77ROUGE-LChain of Summaries (CoS)
2.83085.93049.0312.1296Nov 12, 2025

Evaluation results

MethodLinks
Chain of Summaries (CoS)Backbone=Llama3.2:3B2025.1114.77
Chain of Summaries (CoS)Backbone=GPT-4o-mini2025.1112.69
Chain of Summaries (CoS)Backbone=Qwen2.5:7B2025.1110.71
Zero-shot summaryBackbone=GPT-4o-mini2025.1110.67
Original ContentBackbone=GPT-4o-mini2025.1110
BRIOBackbone=GPT-4o-mini2025.119.25
Chain of DensityBackbone=GPT-4o-mini2025.119.07
Zero-shot summaryBackbone=Llama3.2:3B2025.118.89
PEGASUSBackbone=GPT-4o-mini2025.118.28
Zero-shot summaryBackbone=Qwen2.5:7B2025.117.35
Original ContentBackbone=Qwen2.5:7B2025.116.25
PEGASUSBackbone=Qwen2.5:7B2025.115.92
BRIOBackbone=Llama3.2:3B2025.115.74
BRIOBackbone=Qwen2.5:7B2025.115.74
Chain of DensityBackbone=Qwen2.5:7B2025.115.13
Chain of DensityBackbone=Llama3.2:3B2025.114.63
Original ContentBackbone=Llama3.2:3B2025.114.52
PEGASUSBackbone=Llama3.2:3B2025.113.29