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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present WinoQueer: a benchmark specifically designed to measure whetherlarge language models (LLMs) encode biases that are harmful to the LGBTQ+community. The benchmark is community-sourced, via application of a novelmethod that generates a bias benchmark from a community survey. We apply ourbenchmark to several popular LLMs and find that off-the-shelf models generallydo exhibit considerable anti-queer bias. Finally, we show that LLM bias againsta marginalized community can be somewhat mitigated by finetuning on datawritten about or by members of that community, and that social media textwritten by community members is more effective than news text written about thecommunity by non-members. Our method for community-in-the-loop benchmarkdevelopment provides a blueprint for future researchers to developcommunity-driven, harms-grounded LLM benchmarks for other marginalizedcommunities.

WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models