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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Although chain-of-thought (CoT) prompting combined with language models hasachieved encouraging results on complex reasoning tasks, the naive greedydecoding used in CoT prompting usually causes the repetitiveness and localoptimality. To address this shortcoming, ensemble-optimization tries to obtainmultiple reasoning paths to get the final answer assembly. However, currentensemble-optimization methods either simply employ rule-based post-processingsuch as \textit{self-consistency}, or train an additional model based onseveral task-related human annotations to select the best one among multiplereasoning paths, yet fail to generalize to realistic settings where the type ofinput questions is unknown or the answer format of reasoning paths is unknown.To avoid their limitations, we propose \textbf{self-agreement}, a generalizableensemble-optimization method applying in almost all scenarios where the type ofinput questions and the answer format of reasoning paths may be known orunknown. Self-agreement firstly samples from language model's decoder togenerate a \textit{diverse} set of reasoning paths, and subsequently promptsthe language model \textit{one more time} to determine the optimal answer byselecting the most \textit{agreed} answer among the sampled reasoning paths.Self-agreement simultaneously achieves remarkable performance on six publicreasoning benchmarks and superior generalization capabilities.

Ask One More Time: Self-Agreement Improves Reasoning of Language Models in (Almost) All Scenarios