Hybrid RLHF-AIF: Uncertainty-Guided Routing of Human and AI Feedback for Cost-Efficient Safety Alignment of Large Language Models.

Saved in:
Bibliographic Details
Title: Hybrid RLHF-AIF: Uncertainty-Guided Routing of Human and AI Feedback for Cost-Efficient Safety Alignment of Large Language Models.
Authors: Sun, Tianyu1 (AUTHOR), Li, Yanzhou2 (AUTHOR) lyz19921207@163.com
Source: Mathematics (2227-7390). Oct2026, Vol. 14 Issue 19, p3523. 51p.
Database: Mathematics Source
Full text is not displayed to guests.
Description
ISSN:22277390
DOI:10.3390/math14193523