Papers › Aligning to What? Limits to RLHF Based Alignment
Aligning to What? Limits to RLHF Based Alignment
Logan Barnhart, Reza Akbarian Bafghi, Stephen Becker, Maziar Raissi
Reinforcement Learning from Human Feedback (RLHF) is increasingly used to align large language models (LLMs) with human preferences. However, the effectiveness of RLHF in addressing underlying biases remains unclear. This study investigates the relationship between RLHF and both covert and overt biases in LLMs, particularly focusing on biases against African Americans. We applied various RLHF techniques (DPO, ORPO, and RLOO) to Llama 3 8B and evaluated the covert and overt biases of the resulting models using matched-guise probing and explicit bias testing. We performed additional tests with DPO on different base models and datasets; among several implications, we found that SFT before RLHF calcifies model biases. Additionally, we extend the tools for measuring biases to multi-modal models. Through our experiments we collect evidence that indicates that current alignment techniques are inadequate for nebulous tasks such as mitigating covert biases, highlighting the need for capable datasets, data curating techniques, or alignment tools.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections