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

Human communication relies on common ground (CG), the mutual knowledge andbeliefs shared by participants, to produce coherent and interestingconversations. In this paper, we demonstrate that current response generation(RG) models produce generic and dull responses in dialogues because they actreflexively, failing to explicitly model CG, both due to the lack of CG intraining data and the standard RG training procedure. We introduce Reflect, adataset that annotates dialogues with explicit CG (materialized as inferencesapproximating shared knowledge and beliefs) and solicits 9k diversehuman-generated responses each following one common ground. Using Reflect, weshowcase the limitations of current dialogue data and RG models: less than halfof the responses in current data are rated as high quality (sensible, specific,and interesting) and models trained using this data have even lower quality,while most Reflect responses are judged high quality. Next, we analyze whetherCG can help models produce better-quality responses by using Reflect CG toguide RG models. Surprisingly, we find that simply prompting GPT3 to "think"about CG generates 30% more quality responses, showing promising benefits tointegrating CG into the RG process.

Reflect, Not Reflex: Inference-Based Common Ground Improves Dialogue Response Quality