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

Detecting out-of-distribution (OOD) inputs is crucial for the safe deploymentof natural language processing (NLP) models. Though existing methods,especially those based on the statistics in the feature space of fine-tunedpre-trained language models (PLMs), are claimed to be effective, theireffectiveness on different types of distribution shifts remains underexplored.In this work, we take the first step to comprehensively evaluate the mainstreamtextual OOD detection methods for detecting semantic and non-semantic shifts.We find that: (1) no existing method behaves well in both settings; (2)fine-tuning PLMs on in-distribution data benefits detecting semantic shifts butseverely deteriorates detecting non-semantic shifts, which can be attributed tothe distortion of task-agnostic features. To alleviate the issue, we present asimple yet effective general OOD score named GNOME that integrates theconfidence scores derived from the task-agnostic and task-specificrepresentations. Experiments show that GNOME works well in both semantic andnon-semantic shift scenarios, and further brings significant improvement on twocross-task benchmarks where both kinds of shifts simultaneously take place. Ourcode is available at https://github.com/lancopku/GNOME.

Fine-Tuning Deteriorates General Textual Out-of-Distribution Detection by Distorting Task-Agnostic Features