A three-tier data synthesis method produces realistic and controllable dialogue grounding data, enabling fine-tuned models to achieve consistent improvements on GREC tasks under distribution shift.
Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
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.
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
A three-tier data synthesis method produces realistic and controllable dialogue grounding data, enabling fine-tuned models to achieve consistent improvements on GREC tasks under distribution shift.