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

Large Language Models (LLMs) have emerged as a pivotal force in languagetechnology. Their robust reasoning capabilities and expansive knowledgerepositories have enabled exceptional zero-shot generalization abilities acrossvarious facets of the natural language processing field, including informationretrieval (IR). In this paper, we conduct an in-depth investigation into theutility of documents generated by LLMs for IR. We introduce a simple yeteffective framework, Multi-Text Generation Integration (MuGI), to augmentexisting IR methodologies. Specifically, we prompt LLMs to generate multiplepseudo references and integrate with query for retrieval. The training-freeMuGI model eclipses existing query expansion strategies, setting a new standardin sparse retrieval. It outstrips supervised counterparts like ANCE and DPR,achieving a notable over 18% enhancement in BM25 on the TREC DL dataset and a7.5% increase on BEIR. Through MuGI, we have forged a rapid and high-fidelityre-ranking pipeline. This allows a relatively small 110M parameter retriever tosurpass the performance of larger 3B models in in-domain evaluations, whilealso bridging the gap in out-of-distribution situations. We release our codeand all generated references at https://github.com/lezhang7/Retrieval_MuGI.

MuGI: Enhancing Information Retrieval through Multi-Text Generation Intergration with Large Language Models