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

Zero-shot text rankers powered by recent LLMs achieve remarkable rankingperformance by simply prompting. Existing prompts for pointwise LLM rankersmostly ask the model to choose from binary relevance labels like "Yes" and"No". However, the lack of intermediate relevance label options may cause theLLM to provide noisy or biased answers for documents that are partiallyrelevant to the query. We propose to incorporate fine-grained relevance labelsinto the prompt for LLM rankers, enabling them to better differentiate amongdocuments with different levels of relevance to the query and thus derive amore accurate ranking. We study two variants of the prompt template, coupledwith different numbers of relevance levels. Our experiments on 8 BEIR data setsshow that adding fine-grained relevance labels significantly improves theperformance of LLM rankers.

Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels