English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present BLESS, a comprehensive performance benchmark of the most recentstate-of-the-art large language models (LLMs) on the task of textsimplification (TS). We examine how well off-the-shelf LLMs can solve thischallenging task, assessing a total of 44 models, differing in size,architecture, pre-training methods, and accessibility, on three test sets fromdifferent domains (Wikipedia, news, and medical) under a few-shot setting. Ouranalysis considers a suite of automatic metrics as well as a large-scalequantitative investigation into the types of common edit operations performedby the different models. Furthermore, we perform a manual qualitative analysison a subset of model outputs to better gauge the quality of the generatedsimplifications. Our evaluation indicates that the best LLMs, despite not beingtrained on TS, perform comparably with state-of-the-art TS baselines.Additionally, we find that certain LLMs demonstrate a greater range anddiversity of edit operations. Our performance benchmark will be available as aresource for the development of future TS methods and evaluation metrics.

BLESS: Benchmarking Large Language Models on Sentence Simplification