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.

Why quality eval is the key to search and RAG

1 pointsby codingjaguar3 months ago

1 comment

cratermoon3 months ago
&quot;RAG is based on a very intuitive idea: to avoid LLM’s hallucination, it retrieves the most relevant information from a knowledge base and uses it to ground the LLM’s answer.&quot;<p>Is &quot;avoid&quot; supposed to imply that RAG eliminates the tendency for LLMs to hallucinate? Because it definitely does not, and can not, eliminate hallucinations (or more properly, confabulations) from LLM output.<p>It is in an inherent aspect of these statistical inference machines that they will generate synthetic texts based on an aggregate of token probabilities form a cohort of texts. Sometimes those probabilities will generate token sequences (aka &quot;text&quot;) that has no bearing on reality or facts.