← Back to News arXiv · March 2026

OasisSimp: a yardstick for low-resource sentence simplification

Rewriting official prose into plain language has no yardstick in most languages. Five languages, 9,519 sentences, written by native speakers — the first open evaluation for low-resource simplification. The research page carries the full story: background, method, key figures, and links to the paper.

Research pagearXivPromo copy
5languages
9,519source sentences
~4references per sentence
8open multilingual LLMs
CC BY 4.0license

Information being public does not make it readable. OasisSimp has native speakers build a sentence-simplification benchmark for five languages, making “readable by everyone” measurable.

Launch Highlights

  • Problem：English simplification has years of benchmarks; Thai, Pashto, and Tamil have almost no reusable data.
  • Method：Native speakers created multi-reference simplifications under a shared guideline across five languages.
  • Finding：Few-shot examples help, but low-resource simplification remains far from solved.
  • Why it matters：Public information, education, and accessibility need simplification systems beyond English.

Continue reading

The research page covers the background, method, key figures, and paper links; for quick sharing, use the illustrated promo copy.

Open research pageOpen promo copy