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

Out-of-distribution (OOD) detection is a critical task for reliablepredictions over text. Fine-tuning with pre-trained language models has been ade facto procedure to derive OOD detectors with respect to in-distribution (ID)data. Despite its common use, the understanding of the role of fine-tuning andits necessity for OOD detection is largely unexplored. In this paper, we raisethe question: is fine-tuning necessary for OOD detection? We present a studyinvestigating the efficacy of directly leveraging pre-trained language modelsfor OOD detection, without any model fine-tuning on the ID data. We compare theapproach with several competitive fine-tuning objectives, and offer newinsights under various types of distributional shifts. Extensive evaluations on8 diverse ID-OOD dataset pairs demonstrate near-perfect OOD detectionperformance (with 0% FPR95 in many cases), strongly outperforming itsfine-tuned counterparts. We show that using distance-based detection methods,pre-trained language models are near-perfect OOD detectors when thedistribution shift involves a domain change. Furthermore, we study the effectof fine-tuning on OOD detection and identify how to balance ID accuracy withOOD detection performance. Our code is publically available athttps://github.com/Uppaal/lm-ood.

Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection