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

Augmenting large language models (LLM) to use external tools enhances theirperformance across a variety of tasks. However, prior works over-rely ontask-specific demonstration of tool use that limits their generalizability andcomputational cost due to making many calls to large-scale LLMs. We introduceGEAR, a computationally efficient query-tool grounding algorithm that isgeneralizable to various tasks that require tool use while not relying ontask-specific demonstrations. GEAR achieves better efficiency by delegatingtool grounding and execution to small language models (SLM) and LLM,respectively; while leveraging semantic and pattern-based evaluation at bothquestion and answer levels for generalizable tool grounding. We evaluate GEARon 14 datasets across 6 downstream tasks, demonstrating its stronggeneralizability to novel tasks, tools and different SLMs. Despite offeringmore efficiency, GEAR achieves higher precision in tool grounding compared toprior strategies using LLM prompting, thus improving downstream accuracy at areduced computational cost. For example, we demonstrate that GEAR-augmentedGPT-J and GPT-3 outperform counterpart tool-augmented baselines because ofbetter tool use.

GEAR: Augmenting Language Models with Generalizable and Efficient Tool Resolution