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

Large language models (LLMs) have revolutionized the landscape of NaturalLanguage Processing systems, but are computationally expensive. To reduce thecost without sacrificing performance, previous studies have explored variousapproaches to harness the potential of Small Language Models (SLMs) ascost-effective alternatives to their larger counterparts. Driven by findingsthat SLMs and LLMs exhibit complementary strengths in a structured knowledgeextraction task, this work presents a novel SLM/LLM routing framework designedto improve computational efficiency and enhance task performance. First,exemplar pools are created to represent the types of contexts where each LMprovides a more reliable answer, leveraging a sentence embedding fine-tuned sothat context similarity is close to dialogue state similarity. Then, duringinference, the k-nearest exemplars to the testing instance are retrieved, andthe instance is routed according to majority vote. In dialogue state trackingtasks, the proposed routing framework enhances performance substantiallycompared to relying solely on LLMs, while reducing the computational costs byover 50%.

OrchestraLLM: Efficient Orchestration of Language Models for Dialogue State Tracking