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

Recently, there has been growing interest in using Large Language Models(LLMs) for scientific research. Numerous benchmarks have been proposed toevaluate the ability of LLMs for scientific research. However, currentbenchmarks are mostly based on pre-collected objective questions. This designsuffers from data leakage problem and lacks the evaluation of subjective Q/Aability. In this paper, we propose SciEval, a comprehensive andmulti-disciplinary evaluation benchmark to address these issues. Based onBloom's taxonomy, SciEval covers four dimensions to systematically evaluatescientific research ability. In particular, we design a "dynamic" subset basedon scientific principles to prevent evaluation from potential data leakage.Both objective and subjective questions are included in SciEval. Thesecharacteristics make SciEval a more effective benchmark for scientific researchability evaluation of LLMs. Comprehensive experiments on most advanced LLMsshow that, although GPT-4 achieves SOTA performance compared to other LLMs,there is still substantial room for improvement, especially for dynamicquestions. The data and codes are now publicly available.

SciEval: A Multi-Level Large Language Model Evaluation Benchmark for Scientific Research