🧪 Test?View on arXiv
Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum
fine-tuningmeeting summarizationquery-focusedROUGE
2609.25028
Builder Relevance
1h ago70%
Abstract
This paper discusses the challenges and results of query-focused meeting summarization using the QMSum dataset, highlighting the performance of various systems under a common implementation.
Reality Card
Core Claim
Fine-tuning a 406M Fusion-in-Decoder model on a span regime recovers a loss of 6.30 ROUGE-1 when transitioning from long input to 2,000-word retrieved spans.
Method / Result
The fine-tuned model scores 36.33 ROUGE-1, outperforming a larger 1.2B system which scores 35.41.
Limitations
The absence of a scorer in QMSum makes it difficult to compare results across different systems.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.