PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization.

@inproceedings{zhang-2025-prlm, author = {Kepu Zhang and Teng Shi and Weijie Yu and Jun Xu}, editor = {Meeyoung Cha and Carl Yang and Senjuti Basu Roy and Chanyoung Park and Zhenhui Jessie Li and Noseong Park and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{PrLM: Learning Explicit Reasoning for Personalized RAG via Contrastive Reward Optimization}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {5484--5488}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3760851}, doi = {https://doi.org/10.1145/3746252.3760851} }