Dialogue-Based Generalized Referring Expression Comprehension (GREC) requires models to ground the expression and unlimited targets in complex visual scenes while resolving coreference across a long dialogue context. However, existing systems struggle under distribution shift between training and evaluation domains, a gap exacerbated by the scarcity of annotated dialogue grounding data. We address this challenge with a three-tier data-synthesis method that balances realism and controllability to produce scalable supervision for dialogue-conditioned grounding. Fine-tuning on the synthesized data yields consistent, substantial improvements over prior approaches across standard evaluation metrics.
@article{arxiv.2512.02791,
title = {Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension},
author = {Juexi Shao and Siyou Li and Yujian Gan and Chris Madge and Vanja Karan and Massimo Poesio},
journal= {arXiv preprint arXiv:2512.02791},
year = {2026}
}