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

Language models can be prompted to reason through problems in a manner thatsignificantly improves performance. However, \textit{why} such promptingimproves performance is unclear. Recent work showed that using logically\textit{invalid} Chain-of-Thought (CoT) prompting improves performance almostas much as logically \textit{valid} CoT prompting, and that editing CoT promptsto replace problem-specific information with abstract information orout-of-distribution information typically doesn't harm performance. Criticshave responded that these findings are based on too few and too easily solvedtasks to draw meaningful conclusions. To resolve this dispute, we test whetherlogically invalid CoT prompts offer the same level of performance gains aslogically valid prompts on the hardest tasks in the BIG-Bench benchmark, termedBIG-Bench Hard (BBH). We find that the logically \textit{invalid} reasoningprompts do indeed achieve similar performance gains on BBH tasks as logicallyvalid reasoning prompts. We also discover that some CoT prompts used byprevious works contain logical errors. This suggests that covariates beyondlogically valid reasoning are responsible for performance improvements.

Invalid Logic, Equivalent Gains: The Bizarreness of Reasoning in Language Model Prompting