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.

Ask HN: How Do You Align Evaluator LLMs with Subject Matter Experts?

2 pointsby MutedEstate454 months ago

1 comment

MutedEstate454 months ago
Any LLM developers here struggling with aligning models to subject matter experts (SMEs) or domain-specific expertise? I’m finding it tough to evaluate or quantify how well an LLM aligns with SME expectations. Inspired by the paper "LLMs instead of Human Judges?" (link attached), I’m working on a tool to create a base alignment score using cutting-edge research methodologies. Do you rely on manual reviews, automated metrics a hybrid approach or something else? Or is SME alignment not a big focus for you? Curious to hear your thoughts!