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

To what extent can a neural network systematically reason over symbolicfacts? Evidence suggests that large pre-trained language models (LMs) acquiresome reasoning capacity, but this ability is difficult to control. Recently, ithas been shown that Transformer-based models succeed in consistent reasoningover explicit symbolic facts, under a "closed-world" assumption. However, in anopen-domain setup, it is desirable to tap into the vast reservoir of implicitknowledge already encoded in the parameters of pre-trained LMs. In this work,we provide a first demonstration that LMs can be trained to reliably performsystematic reasoning combining both implicit, pre-trained knowledge andexplicit natural language statements. To do this, we describe a procedure forautomatically generating datasets that teach a model new reasoning skills, anddemonstrate that models learn to effectively perform inference which involvesimplicit taxonomic and world knowledge, chaining and counting. Finally, we showthat "teaching" models to reason generalizes beyond the training distribution:they successfully compose the usage of multiple reasoning skills in singleexamples. Our work paves a path towards open-domain systems that constantlyimprove by interacting with users who can instantly correct a model by addingsimple natural language statements.

Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge