Liu, Z., Khajavi, S. H., Jiang, G., & Liu, X. (2026). Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 37692–37700. https://doi.org/10.1609/aaai.v40i44.41104