Reinforcement learning on synthetic data improves language models' ability to represent and use common ground with relational references in situated dialogs.
The style might be different
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs
Reinforcement learning on synthetic data improves language models' ability to represent and use common ground with relational references in situated dialogs.