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

Recent zero-shot evaluations have highlighted important limitations in theabilities of language models (LMs) to perform meaning extraction. However, itis now well known that LMs can demonstrate radical improvements in the presenceof experimental contexts such as in-context examples and instructions. How welldoes this translate to previously studied meaning-sensitive tasks? We present acase-study on the extent to which experimental contexts can improve LMs'robustness in performing property inheritance -- predicting semantic propertiesof novel concepts, a task that they have been previously shown to fail on. Uponcarefully controlling the nature of the in-context examples and theinstructions, our work reveals that they can indeed lead to non-trivialproperty inheritance behavior in LMs. However, this ability is inconsistent:with a minimal reformulation of the task, some LMs were found to pick up onshallow, non-semantic heuristics from their inputs, suggesting that thecomputational principles of semantic property inference are yet to be masteredby LMs.

Experimental Contexts Can Facilitate Robust Semantic Property Inference in Language Models, but Inconsistently