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

This work addresses the challenge of democratizing advanced Large LanguageModels (LLMs) by compressing their mathematical reasoning capabilities intosub-billion parameter Small Language Models (SLMs) without compromisingperformance. We introduce Equation-of-Thought Distillation (EoTD), a noveltechnique that encapsulates the reasoning process into equation-basedrepresentations to construct an EoTD dataset for fine-tuning SLMs.Additionally, we propose the Mix Thoughts Distillation (MTD) framework toenhance the reasoning performance of SLMs. This involves creating a reasoningdataset with multiple thought processes and using it for fine-tuning. Ourexperimental findings demonstrate that EoTD significantly boosts the reasoningabilities of SLMs, while MTD enables these models to achieve state-of-the-artreasoning performance.

Improving Small Language Models' Mathematical Reasoning via Mix Thoughts Distillation