Skip to content
AI News HubLIVE
Original source2 min read

Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum

Summary

QMSum provides no scorer, making query-focused meeting summarization results hard to compare. This paper rescoring or generating 15 systems under one implementation. Through a common inference port, a released 406M Fusion-in-Decoder specialist loses 6.30 ROUGE-1 when moved from capped long input to 2,000-word retrieved spans, but fine-tuning on that span regime recovers the loss. On test it scores 36.33 ROUGE-1 versus 35.41 for a 1.2B system, with a meeting-cluster 95% interval of [-0.27, +2.22], so QMSum does not statistically separate them; the smaller system uses about one-third the parameters and less than half the peak inference memory. Within the fixed 1.2B base, span-regime fine-tuning adds 5.29 [+4.02, +6.56], and replacing the first 4,500 transcript words with 2,000 retrieved wor…

SourcearXiv Computational LinguisticsAuthor: Edward Xi Yang (Ertas AI)
Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Aug 2026]

Title:Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum

View a PDF of the paper titled Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum, by Edward Xi Yang (Ertas AI)

View PDF HTML (experimental)

Abstract:QMSum provides no scorer, making query-focused meeting summarization results difficult to compare. We rescore or generate 15 systems under one implementation. Through a common inference port, a released 406M Fusion-in-Decoder specialist loses 6.30 ROUGE-1 when moved from capped long input to 2,000-word retrieved spans. Fine-tuning it on this span regime recovers the loss. On test it scores 36.33 ROUGE-1 versus 35.41 for our 1.2B system; the meeting-cluster 95% interval for the difference is [-0.27, +2.22], so QMSum does not statistically separate them. The smaller system uses about one-third as many total parameters and less than half the peak inference memory. Within the fixed 1.2B base, span-regime fine-tuning adds 5.29 [+4.02, +6.56], while replacing the first 4,500 transcript words with 2,000 retrieved words adds 1.55 on test and 0.29 on validation. Separately, under one concise prompt and reference-overlap scorer, a released 406M specialist exceeds five proprietary hosted models by at least 6.2 ROUGE-1, but output length and absent human or factuality evaluation limit this ordering. Conclusions are limited to QMSum and automatic metrics.

Comments: 24 pages, 4 figures

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2609.25028 [cs.CL]

(or arXiv:2609.25028v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.25028

arXiv-issued DOI via DataCite

Submission history

From: Edward Xi Yang [view email] [v1] Tue, 18 Aug 2026 04:26:31 UTC (181 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Retrieved-Span Training for Efficient Query-Focused Meeting Summarization on QMSum, by Edward Xi Yang (Ertas AI)

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

InvestorsAdvanced

Key points

  • QMSum has no scorer, so the paper rescoring or generating 15 systems under a single implementation.
  • A 406M specialist loses 6.30 ROUGE-1 when moved to 2,000-word retrieved spans, but span-regime fine-tuning recovers the loss.
  • On test the 406M model scores 36.33 versus 35.41 for a 1.2B system, with a 95% interval of [-0.27, +2.22], using far fewer parameters and less memory.
  • Under one concise prompt the 406M specialist beats five proprietary hosted models by at least 6.2 ROUGE-1, but evaluation limits constrain the ordering.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models