cd /news/large-language-models/document-summarization-for-ai-based-… · home topics large-language-models article
[ARTICLE · art-118864] src=aclanthology.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Document Summarization for AI-based Post-Editing

Researchers at the Association for Machine Translation in the Americas found that document-level summaries improve AI-based post-editing quality only when they are specific and actionable, with gemini-2.5-flash-lite summaries yielding gains in edit distance and modest COMET gains, while GPT-4o summaries degraded performance across most metrics. The study, presented at AMTA 2026, evaluated nine LLMs from OpenAI and Google across 448 documents, 37 target locales, and 13 content domains, showing the positive effect was most pronounced in terminologically dense domains and lower-resource locales.

read2 min views9 publishedSep 1, 2026
Document Summarization for AI-based Post-Editing
Image: Aclanthology (auto-discovered)
[Document Summarization for AI-based Post-Editing](https://aclanthology.org/2026.amta-research.11.pdf)

[Vera Senderowicz Guerra](/people/vera-senderowicz-guerra/unverified/),
[Dimitrios Pavlou](/people/dimitrios-pavlou/unverified/),
[Peter Bourgonje](/people/peter-bourgonje/unverified/),
[Olesia Khrapunova](/people/olesia-khrapunova/unverified/),
[Konstantinos Karageorgos](/people/konstantinos-karageorgos/unverified/),
[Aaron Schliem](/people/aaron-schliem/unverified/)
Abstract

Post-Editing (PE) is typically performed on isolated segments or small batches, without access to broader document context. In this paper, we investigate whether pre-generated, document-level summaries can improve PE quality. Using a purpose-built summarization prompt evaluated across nine LLMs from OpenAI and Google, we select two models with contrasting summary styles for downstream experiments on 448 documents covering 37 target locales and 13 content domains. Summaries generated by gemini-2.5-flash-lite, which are directive and domain-specific, yield gains in edit distance and modest gains in COMET, whereas those generated by GPT-4o, which tend to be more generic and descriptive, degrade performance across most metrics. The positive effect appears most pronounced in terminologically dense domains and lower-resource locales. A qualitative analysis shows that improvements arise when summaries provide specific, actionable guidance on terminology, domain conventions, and style, and that performance decreases when summaries are underspecified or conflicting. These findings suggest that summary specificity and actionability, rather than the mere addition of context, determine whether document-level information benefits post-editing.- Anthology ID:

- 2026.amta-research.11
- Volume:
[Proceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)](/volumes/2026.amta-research/)- Month:
  • August
  • Year:
  • 2026
  • Address:
  • Québec City, Canada
- Editors:
[Eleftheria Briakou](/people/eleftheria-briakou/unverified/),[Jeremy Gwinnup](/people/jeremy-gwinnup/),[Shivali Goel](/people/shivali-goel/unverified/)- Venue:
[AMTA](/venues/amta/)- SIG:
- Publisher:
  • Association for Machine Translation in the Americas
- Note:
- Pages:
  • 174–185
- Language:
- URL:
[https://aclanthology.org/2026.amta-research.11/](https://aclanthology.org/2026.amta-research.11/)- DOI:
- Cite (ACL):
  • Vera Senderowicz Guerra, Dimitrios Pavlou, Peter Bourgonje, Olesia Khrapunova, Konstantinos Karageorgos, and Aaron Schliem. 2026. Document Summarization for AI-based Post-Editing. InProceedings of the 17th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pages 174–185, Québec City, Canada. Association for Machine Translation in the Americas. - Cite (Informal):
[Document Summarization for AI-based Post-Editing](https://aclanthology.org/2026.amta-research.11/)(Guerra et al., AMTA 2026)- PDF:
[https://aclanthology.org/2026.amta-research.11.pdf](https://aclanthology.org/2026.amta-research.11.pdf)
── more in #large-language-models 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/document-summarizati…] indexed:0 read:2min 2026-09-01 ·