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

Some interpersonal verbs can implicitly attribute causality to either theirsubject or their object and are therefore said to carry an implicit causality(IC) bias. Through this bias, causal links can be inferred from a narrative,aiding language comprehension. We investigate whether pre-trained languagemodels (PLMs) encode IC bias and use it at inference time. We find that to bethe case, albeit to different degrees, for three distinct PLM architectures.However, causes do not always need to be implicit -- when a cause is explicitlystated in a subordinate clause, an incongruent IC bias associated with the verbin the main clause leads to a delay in human processing. We hypothesize thatthe temporary challenge humans face in integrating the two contradictingsignals, one from the lexical semantics of the verb, one from thesentence-level semantics, would be reflected in higher error rates for modelson tasks dependent on causal links. The results of our study lend support tothis hypothesis, suggesting that PLMs tend to prioritize lexical patterns overhigher-order signals.

John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs