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

Ensuring that large language models (LMs) are fair, robust and usefulrequires an understanding of how different modifications to their inputs impactthe model's behaviour. In the context of open-text generation tasks, however,such an evaluation is not trivial. For example, when introducing a model withan input text and a perturbed, "contrastive" version of it, meaningfuldifferences in the next-token predictions may not be revealed with standarddecoding strategies. With this motivation in mind, we propose Contrastive InputDecoding (CID): a decoding algorithm to generate text given two inputs, wherethe generated text is likely given one input but unlikely given the other. Inthis way, the contrastive generations can highlight potentially subtledifferences in how the LM output differs for the two inputs in a simple andinterpretable manner. We use CID to highlight context-specific biases that arehard to detect with standard decoding strategies and quantify the effect ofdifferent input perturbations.

Surfacing Biases in Large Language Models using Contrastive Input Decoding