Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment
Lists
Only you see this
BibTeX
@inproceedings{liu2026targeting,
author = {Zixuan Liu and Siavash H. Khajavi and Guangkai Jiang and Xinru Liu},
title = {{Targeting Misalignment: A Conflict-Aware Framework for Reward-Model-based LLM Alignment}},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2026},
doi = {10.1609/aaai.v40i44.41104},
}Loading related content...