TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Does few-shot tool assistance work? (e.g., Self-Ask, RARR, ReAct, Art)

2 pointsby momojo11 months ago

1 comment

momojo11 months ago
tl;dr<p>&gt; Overall, we found that few-shot tool assistance, without explicitly training models to use tools, is a difficult and unsolved problem, with significant costs. This is in contrast to their commonly perceived value as an easy and cheap solution to augment LMs with tools, such as retrieval or calculation. Beyond few-shot strategies, training models to use tools seems to be more promising (and a popular paradigm in recent months — such as with Gemini, GPT-4 and Command-R).