MO-IKE models prompt construction as a constrained Markov decision process via multi-objective RL, raising edit success on Llama-3.2 from 85.0% to 92.0%, paraphrase consistency from 77% to 79%, and retention by 23.0%
The work proposes MO-IKE, a multi-objective reinforcement learning algorithm that formulates prompt construction for in-context knowledge editing as a Constrained Markov Decision Process and trains a dynamic retriever to optimize competing objectives of reliability, generality, and specificity, improving edit success on Llama-3.2 from 85.0% to 92.0%, paraphrase consistency from 77% to 79%, and retention rate by 23.0% over prior RL-based methods.