[2601.09365] Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs

[2601.09365] Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs

arXiv - AI 4 min read

About this article

Abstract page for arXiv paper 2601.09365: Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs

Computer Science > Computation and Language arXiv:2601.09365 (cs) [Submitted on 14 Jan 2026 (v1), last revised 7 Apr 2026 (this version, v2)] Title:Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs Authors:Biswesh Mohapatra, Théo Charlot, Giovanni Duca, Mayank Palan, Laurent Romary, Justine Cassell View a PDF of the paper titled Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs, by Biswesh Mohapatra and 5 other authors View PDF HTML (experimental) Abstract:Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction in a shared space and over time. With the increasing presence of embodied conversational agents and social robots, the ability to correctly ground this kind of conversational content in order to refer back later also becomes important for dialog systems. Prior studies have demonstrated that LLMs are capable of performing certain grounding acts like acknowledgments. However, relatively little work has investigated their capacity to leverage the grounded information, like in complex scenarios involving space and time (e.g., "let's go to that café near the park we went to yesterday"). To that end, in this work, we evaluate a model's ability to establish common ground by utilizing these "relational references" in the dynamic and sh...

Originally published on April 08, 2026. Curated by AI News.

Related Articles

CONESTOGA COLLEGE Robots deepen AI and data analytics training for Conestoga students
Machine Learning

CONESTOGA COLLEGE Robots deepen AI and data analytics training for Conestoga students

AI News - General · 5 min ·
[2602.00185] QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities
Llms

[2602.00185] QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities

Abstract page for arXiv paper 2602.00185: QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities

arXiv - AI · 4 min ·
[2510.25241] One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors
Machine Learning

[2510.25241] One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors

Abstract page for arXiv paper 2510.25241: One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors

arXiv - AI · 3 min ·
[2604.06124] Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
Llms

[2604.06124] Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery

Abstract page for arXiv paper 2604.06124: Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat...

arXiv - AI · 4 min ·
More in Robotics: This Week Guide Trending

No comments

No comments yet. Be the first to comment!

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Daily or weekly digest • Unsubscribe anytime