Discussion
Loading...

Post

Log in
  • Sign up
  • About
  • Code of conduct
  • Privacy
  • Users
  • Instances
  • About Bonfire
sayzard
sayzard
@sayzard@mastodon.sayzard.org  ·  activity timestamp 5 days ago

fly51fly (@fly51fly)

2026년 UC Berkeley 연구진(T A Qiu, M Carroll, C Allen)의 arXiv 논문 'Truthfulness Despite Weak Supervision'은 약한 감독 환경에서 동료 예측(peer prediction)을 활용해 대형언어모델(LLM)의 진실성(truthfulness)을 평가하고 훈련하는 방법을 제안·검증합니다. 약한 라벨링 상황에서도 진실성 개선을 노린 평가·학습 프레임워크 연구입니다.

https://x.com/fly51fly/status/2016990237097144576

#truthfulness #weaksupervision #llm #peerprediction #research

X (formerly Twitter)
View
  • Copy link
  • Flag this post
  • Block

Indieweb Studio

This is a relaxed, online social space for the indieweb community, brought to you by indieweb.social.

Please abide by our code of conduct and have a nice time!

Indieweb Studio: About · Code of conduct · Privacy · Users · Instances
Bonfire social · 1.0.2-alpha.7 no JS en
Automatic federation enabled
Log in Create account
  • Explore
  • About
  • Members
  • Code of Conduct