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

Causal reasoning, the ability to identify cause-and-effect relationship, iscrucial in human thinking. Although large language models (LLMs) succeed inmany NLP tasks, it is still challenging for them to conduct complex causalreasoning like abductive reasoning and counterfactual reasoning. Given the factthat programming code may express causal relations more often and explicitlywith conditional statements like ``if``, we want to explore whether Code-LLMsacquire better causal reasoning abilities. Our experiments show that comparedto text-only LLMs, Code-LLMs with code prompts are significantly better incausal reasoning. We further intervene on the prompts from different aspects,and discover that the programming structure is crucial in code prompt design,while Code-LLMs are robust towards format perturbations.

The Magic of IF: Investigating Causal Reasoning Abilities in Large Language Models of Code