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

Chain-of-Thought (CoT) and Program-Aided Language Models (PAL) represent twodistinct reasoning methods, each with its own strengths. CoT employs naturallanguage, offering flexibility and interpretability, while PAL utilizesprogramming language, yielding more structured and rigorous logic. We introducea model selection method to combine the best of both worlds by employing alarge language model (LLM) to dynamically select between them. Our theoreticalanalysis underscores the feasibility of this method, which is furthercorroborated by empirical results. Our proposed method demonstrates significantperformance improvements across eight reasoning datasets with Codex, ChatGPT,and GPT-4. Additionally, our method is complementary to self-consistency; whenintegrated, it can further enhance performance while significantly reducingcomputation costs. Moreover, we achieve new state-of-the-art results on GSM8Kand SVAMP, with respective accuracies of 96.8% and 93.7%. Our code, data andprompts are available at https://github.com/XuZhao0/Model-Selection-Reasoning

Automatic Model Selection with Large Language Models for Reasoning