MEAV: Model Editing with Alignment Vectors for inference time LLM alignment in single and multidomain preference spectrum

Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing trainingtime alignment methods require full re-training when a change is needed and inference-time ones typically require access to the reward model at each inference step. We introduce MEAV, an inference-time model-editingbased LLM alignment method that learns encoded representations of preference dimensions, called Alignment Vectors (AV). These representations enable dynamic adjusting of the model behavior during inference through simple linear operations. Here, we focus on three gradual response levels across three specialized domains: medical, legal, and financial, exemplifying its practical potential. This new alignment paradigm introduces adjustable preference knobs during inference, allowing users to tailor their LLM outputs while reducing the inference cost by half compared to the prompt engineering approach. Additionally, we find that AVs are transferable across different finetuning stages of the same model, demonstrating their flexibility. AVs also facilitate multidomain, diverse preference alignment, making the process 12x faster than the retraining approach.