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

Large language models (LLMs), like ChatGPT and GPT-4, have demonstratedremarkable abilities in natural language understanding and generation. However,alongside their positive impact on our daily tasks, they can also produceharmful content that negatively affects societal perceptions. To systematicallyassess the safety of Chinese LLMs, we introduce SuperCLUE-Safety (SC-Safety) -a multi-round adversarial benchmark with 4912 open-ended questions coveringmore than 20 safety sub-dimensions. Adversarial human-model interactions andconversations significantly increase the challenges compared to existingmethods. Experiments on 13 major LLMs supporting Chinese yield the followinginsights: 1) Closed-source models outperform open-sourced ones in terms ofsafety; 2) Models released from China demonstrate comparable safety levels toLLMs like GPT-3.5-turbo; 3) Some smaller models with 6B-13B parameters cancompete effectively in terms of safety. By introducing SC-Safety, we aim topromote collaborative efforts to create safer and more trustworthy LLMs. Thebenchmark and findings provide guidance on model selection. Our benchmark canbe found at https://www.CLUEbenchmarks.com

SC-Safety: A Multi-round Open-ended Question Adversarial Safety Benchmark for Large Language Models in Chinese