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

Generating intermediate steps, or Chain of Thought (CoT), is an effective wayto significantly improve language models' (LM) multi-step reasoning capability.However, the CoT lengths can grow rapidly with the problem complexity, easilyexceeding the maximum context size. Instead of increasing the context limit,which has already been heavily investigated, we explore an orthogonaldirection: making LMs divide a problem into multiple contexts. We propose a newinference framework, called Recursion of Thought (RoT), which introducesseveral special tokens that the models can output to trigger context-relatedoperations. Extensive experiments with multiple architectures including GPT-3show that RoT dramatically improves LMs' inference capability to solveproblems, whose solution consists of hundreds of thousands of tokens.

Recursion of Thought: A Divide-and-Conquer Approach to Multi-Context Reasoning with Language Models