RLTHF: Targeted Human Feedback for LLM Alignment
Yifei Xu, Tusher Chakraborty, Emre Kiciman, Bibek Aryal, Srinagesh Sharma, Songwu Lu, Ranveer Chandra
Abstract
Fine-tuning large language models (LLMs) to align with user preferences is challenging due to the high cost of quality human annotations in Reinforcement Learning from Human Feedback (RLHF) and the generalizability limitations of AI Feedback. To address these challenges, we propose RLTHF, a human-AI hybrid framework that combines LLM-based initial alignment with selective human annotations to achieve full-human annotation alignment with minimal effort. RLTHF identifies hard-to-annotate samples mislabeled by LLMs using a reward model's reward distribution and iteratively enhances alignment by integrating strategic human corrections while leveraging LLM's correctly labeled samples. Evaluations on HH-RLHF and TL;DR datasets show that RLTHF reaches full-human annotation-level alignment with only 6-7% of the human annotation effort. Furthermore, models trained on RLTHF's curated datasets for downstream tasks outperform those trained on fully human-annotated datasets, underscoring the effectiveness of RLTHF.
BibTeX
@inproceedings{
xu2025rlthf,
title={{RLTHF}: Targeted Human Feedback for {LLM} Alignment},
author={Yifei Xu and Tusher Chakraborty and Emre Kiciman and Bibek Aryal and Srinagesh Sharma and Songwu Lu and Ranveer Chandra},
booktitle={Forty-second International Conference on Machine Learning},
year={2025},
url={https://openreview.net/forum?id=ATUfSZayVo}
}