RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce.

@inproceedings{chen-2026-raddpo, author = {Zhiguo Chen and Guohao Sun and Yiming Qiu and Abel Salinas and Yangqi Zhang and Xingzhi Yao and Mingming Li and Huimu Wang and Abel Salinas and Yangqi Zhang and Songlin Wang and Sulong Xu}, editor = {Hannah Bast and Alistair Moffat and Falk Scholer and Marc Najork and Min Zhang and Hannah Bast and Marc Najork and Min Zhang}, title = {{RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {4507--4512}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3808512}, doi = {https://doi.org/10.1145/3805712.3808512} }