Beyond Training Objectives: Interpreting Reward Model Divergence in Large Language Models
Large language models (LLMs) fine-tuned by reinforcement learning from human feedback (RLHF) are becoming more widely deployed. We coin the term $\textit{Implicit Reward Model}$ (IRM) to refer to the changes that occur to an LLM during RLHF that result in high-reward generations. We interpret IRMs, and measure their divergence from the RLHF reward model used in the fine-tuning process that induced them. By fitting a linear function to an LLM's IRM, a reward model with the same type signature as the RLHF reward model is constructed, allowing for direct comparison. Additionally, we validate our construction of the IRM through cross-comparison with classifications of features generated by an LLM based on their relevance to the RLHF reward model. Better comprehending IRMs can help minimize discrepencies between LLM behavior and training objectives, which we believe to be an essential component of the $\textit{safety}$ and $\textit{alignment}$ of LLMs.
PDF Abstract