SEAL: Systematic Error Analysis for Value ALignment

Reinforcement Learning from Human Feedback (RLHF) aims to align language models (LMs) with human values by training reward models (RMs) on binary preferences and using these RMs to fine-tune the base LMs. Despite its importance, the internal mechanisms of RLHF remain poorly understood. This paper introduces new metrics to evaluate the effectiveness of modeling and aligning human values, namely feature imprint, alignment resistance and alignment robustness. We categorize alignment datasets into target features (desired values) and spoiler features (undesired concepts). By regressing RM scores against these features, we quantify the extent to which RMs reward them - a metric we term feature imprint. We define alignment resistance as the proportion of the preference dataset where RMs fail to match human preferences, and we assess alignment robustness by analyzing RM responses to perturbed inputs. Our experiments, utilizing open-source components like the Anthropic/hh-rlhf preference dataset and OpenAssistant RMs, reveal significant imprints of target features and a notable sensitivity to spoiler features. We observed a 26% incidence of alignment resistance in portions of the dataset where LM-labelers disagreed with human preferences. Furthermore, we find that misalignment often arises from ambiguous entries within the alignment dataset. These findings underscore the importance of scrutinizing both RMs and alignment datasets for a deeper understanding of value alignment.