PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
September 30, 20250 citationsOpen Access

Text Adaptation to Plain Language and Easy Read via Automatic Post-Editing Cycles

View Full Paper
JCJesús CallejaDPDavid PonceTEThierry Etchegoyhen

Key Points

  • Vicomtech's system achieved first and second place in adaptation metrics for plain language and easy read.
  • Iterative automatic post-editing of large language models resulted in significant improvements in text readability.
  • Readability and similarity metrics guided the refinement process until no further adaptations were effective.
  • The system focused on Spanish texts, demonstrating the effectiveness of automated processes in producing accessible content.

Abstract

We describe Vicomtech's participation in the CLEARS challenge on text adaptation to Plain Language and Easy Read in Spanish. Our approach features automatic post-editing of different types of initial Large Language Model adaptations, where successive adaptations are generated iteratively until readability and similarity metrics indicate that no further adaptation refinement can be successfully performed. Taking the average of all official metrics, our submissions achieved first and second place in Plain language and Easy Read adaptation, respectively.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Calleja et al. (2025) studied this question.

synapsesocial.com/papers/68dc12cc8a7d58c25ebb0c5dhttps://doi.org/10.48550/arxiv.2509.11991
Ask AI
Helpful
Bookmark
Share
View Full Paper

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Exploring Large Language Models to generate Easy to Read content2024
  2. 2Benchmark of small language models for plain-language simplification in Spanish clinical texts2026
  3. 3Plain Language Adaptations of Biomedical Text Using LLMs: Comparision of Evaluation Metrics.2025
  4. 4ReadCtrl: Personalizing text generation with readability-controlled instruction learning2024 · 1 citations
  5. 5Easy-read and large language models: on the ethical dimensions of LLM-based text simplification2024 · 19 citations