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

Answering complex questions is a challenging task that requires questiondecomposition and multistep reasoning for arriving at the solution. Whileexisting supervised and unsupervised approaches are specialized to a certaintask and involve training, recently proposed prompt-based approaches offergeneralizable solutions to tackle a wide variety of complex question-answering(QA) tasks. However, existing prompt-based approaches that are effective forcomplex QA tasks involve expensive hand annotations from experts in the form ofrationales and are not generalizable to newer complex QA scenarios and tasks.We propose, icat (In-Context Ability Transfer) which induces reasoningcapabilities in LLMs without any LLM fine-tuning or manual annotation ofin-context samples. We transfer the ability to decompose complex questions tosimpler questions or generate step-by-step rationales to LLMs, by carefulselection from available data sources of related tasks. We also propose anautomated uncertainty-aware exemplar selection approach for selecting examplesfrom transfer data sources. Finally, we conduct large-scale experiments on avariety of complex QA tasks involving numerical reasoning, compositionalcomplex QA, and heterogeneous complex QA which require decomposed reasoning. Weshow that ICAT convincingly outperforms existing prompt-based solutions withoutinvolving any model training, showcasing the benefits of re-using existingabilities.

In-Context Ability Transfer for Question Decomposition in Complex QA