Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs
This addresses a challenge in dialog systems for enabling coherent interactions, but it is incremental as it builds on prior work on grounding acts in LLMs.
The paper tackles the problem of representing and storing common ground in situational dialogues for dialog systems, evaluating multiple methods and proposing improvements for establishing and using common ground.
Common ground plays a critical role in situated spoken dialogues, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction. For dialog systems, the ability to correctly ground conversational content in order to refer back to it later is particularly important. Prior studies have demonstrated that LLMs are capable of performing grounding acts such as requesting clarification or producing acknowledgments, yet relatively little work has investigated how common ground can be explicitly represented and stored for later use. Without such mechanisms, it remains unclear whether acknowledgment or clarification behaviors truly reflect a grounded understanding. In this work, we evaluate a model's ability to establish and exploit common ground through relational references to entities within the shared context in a situational dialogue. We test multiple methods for representing common ground in situated dialogues and further propose approaches to improve both the establishment of common ground and its subsequent use in the conversation.