Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning.

@inproceedings{yuan-2026-kardiar1, author = {Jiahao Yuan and Zhiqing Cui and Hanqing Wang and Yuansheng Gao and Yucheng Zhou and Usman Naseem}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Kardia-R1: Unleashing LLMs to Reason toward Understanding and Empathy for Emotional Support via Rubric-as-Judge Reinforcement Learning}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {9230--9240}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3793022}, doi = {https://doi.org/10.1145/3774904.3793022} }