When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming

Abstract

Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies. The same substitution creates a structured failure surface: optimization can raise the learned reward while external quality falls, degrade both proxy and judge scores, reveal proxy under-alignment, or produce evaluator-specific disagreement. We present an empirical failure-mode study of a compact RLHF pipeline with proximal policy optimization (PPO), direct preference optimization (DPO), uncertainty-penalized PPO (UP-PPO), reward-model uncertainty, approximate policy drift, diversity and repetition diagnostics, and two external LLM judges. Rather than treating reward hacking as a single terminal event, we classify matched transitions between checkpoints using the directions of the learned reward, judge scores, and average judge score. Across 61 checkpoint rows and 1920 row-level transitions, aggressive PPO has the highest localized reward-hacking rate (14.45%; bootstrap 95% CI: 10.16-18.75), while UP-PPO yields lower rates in the same aggressive regime (11.33-10.94%). A pre-transition logistic model predicts future row-level reward hacking with ROC-AUC 0.821, and row-level analysis finds localized reward hacking that checkpoint averages miss in 3 of 12 settings. The central conclusion is methodological: RLHF failures are not only final-model pathologies, but training dynamics that can be classified, localized, and partially anticipated.