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.

Training and aligning LLMs with RLHF and RLHF alternatives

102 pointsby rasbtover 1 year ago

2 comments

scoresmokeover 1 year ago
Discussions about LLM alignment often miss topics of data quality and quantity. It turns out that current models like Llama 2 use 10K+ prompts and responses for supervised fine-tuning (SFT) and 100K+ human preference pairs. While the preferences are pretty easy to annotate, producing a good SFT dataset is uneasy.<p><a href="https:&#x2F;&#x2F;evalovernite.substack.com&#x2F;p&#x2F;rlhf-math-aint-enough" rel="nofollow noreferrer">https:&#x2F;&#x2F;evalovernite.substack.com&#x2F;p&#x2F;rlhf-math-aint-enough</a><p><a href="https:&#x2F;&#x2F;doi.org&#x2F;10.5281&#x2F;zenodo.8186168" rel="nofollow noreferrer">https:&#x2F;&#x2F;doi.org&#x2F;10.5281&#x2F;zenodo.8186168</a>
jamesblondeover 1 year ago
I read here that Yann LeCun claimed that even with RLHF, LLMs will still hallucinate - that it&#x27;s an unavoidable consequence of their autoregressive nature<p><a href="https:&#x2F;&#x2F;www.hopsworks.ai&#x2F;dictionary&#x2F;rlhf-reinforcement-learning-from-human-feedback" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.hopsworks.ai&#x2F;dictionary&#x2F;rlhf-reinforcement-learn...</a>
评论 #37458973 未加载
评论 #37458947 未加载
评论 #37462170 未加载
评论 #37462876 未加载