Reinforcement Learning with Verbalized Probabilities for LLM Classification.

@inproceedings{li-2026-reinforcement, author = {Liyao Li and Hao Chen and Jiaming Tian and Wentao Ye and Lirong Gao and Chao Ye and Ningtao Wang and Xing Fu and Yu Cheng and Haobo Wang and Gang Chen and Junbo Zhao}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{Reinforcement Learning with Verbalized Probabilities for LLM Classification}}, 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 = {7401--7411}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792540}, doi = {https://doi.org/10.1145/3774904.3792540} }