Zero-Shot (GPT-4o)

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Knowledge Base5 results

Text SummarizationonBookSum
ROUGE-1· 2025-01-03
20.3
best: 42.51 (NexusSum (Mistral Large))
SOTA
End-to-End Long Document Summarization using Gradient Caching arXiv:2501.01805
Text SummarizationonBookSum
ROUGE-L· 2025-01-03
17.68
best: 23.91 (NexusSum (Mistral Large))
SOTA
End-to-End Long Document Summarization using Gradient Caching arXiv:2501.01805
Text SummarizationonBookSum
BERTScore (F1)· 2025-01-03
47.24
best: 70.7 (NexusSum (Mistral Large))
End-to-End Long Document Summarization using Gradient Caching arXiv:2501.01805
Text SummarizationonBookSum
ROUGE-2· 2025-01-03
3.5
best: 10.53 (Echoes-Extractive-Abstractive)
End-to-End Long Document Summarization using Gradient Caching arXiv:2501.01805
Text SummarizationonMENSA
BERTScore (F1)· 2025-01-03
52.8
best: 65.73 (NexusSum (Mistral Large))
End-to-End Long Document Summarization using Gradient Caching arXiv:2501.01805