# Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs

arXiv: https://arxiv.org/abs/2601.09365 · HTML: https://mlsanity.com/paper/2601.09365/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 53 references that are in the map.
- First posted on arXiv 14 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Retrieval Augmentation Reduces Hallucination in Conversation](https://mlsanity.com/paper/2104.07567/) (2021)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Tracking the World State with Recurrent Entity Networks](https://mlsanity.com/paper/1612.03969/) (2016)
- [Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions](https://mlsanity.com/paper/2010.10216/) (2020)
- [Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends](https://mlsanity.com/paper/2406.03487/) (2024)
- [MeetUp! A Corpus of Joint Activity Dialogues in a Visual Environment](https://mlsanity.com/paper/1907.05084/) (2019)
- [DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications](https://mlsanity.com/paper/2409.19020/) (2024)
- [Common Ground Tracking in Multimodal Dialogue](https://mlsanity.com/paper/2403.17284/) (2024)
- [Conversational Grounding: Annotation and Analysis of Grounding Acts and Grounding Units](https://mlsanity.com/paper/2403.16609/) (2024)
- [Learning End-to-End Goal-Oriented Dialog with Maximal User Task Success and Minimal Human Agent Use](https://mlsanity.com/paper/1907.07638/) (2019)
- [The Spot the Difference corpus: a multi-modal corpus of spontaneous task oriented spoken interactions](https://mlsanity.com/paper/1805.05091/) (2018)
- [Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling](https://mlsanity.com/paper/2209.07634/) (2022)
- [GraphWOZ: Dialogue Management with Conversational Knowledge Graphs](https://mlsanity.com/paper/2211.12852/) (2022)
- [Referential ambiguity and clarification requests: comparing human and LLM behaviour](https://mlsanity.com/paper/2507.10445/) (2025)

## Built on by (most cited first, 2 of 2)

- [Using Machine Mental Imagery for Representing Common Ground in Situated Dialogue](https://mlsanity.com/paper/2604.21144/) (2026)
- [Knowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents](https://mlsanity.com/paper/2610.18684/) (2026)

## Abstract (arXiv)

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 caf'e 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 shared environments of situated dialogs. We then test multiple methods for representing common ground and further propose approaches to improve their performance by using reinforcement learning on our synthetically generated dialog data .