Reward Shaping for Robust Refusal in Small Language Models for Retrieval-Augmented Question Answering.

@inproceedings{rajapakse-2026-reward, author = {Thilina Chaturanga Rajapakse and Maarten de Rijke}, 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 = {{Reward Shaping for Robust Refusal in Small Language Models for Retrieval-Augmented Question Answering}}, booktitle = {{Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2026, MelbourneVICAustralia, July 20-24, 2026}}, pages = {4064--4068}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3805712.3809891}, doi = {https://doi.org/10.1145/3805712.3809891} }