# Dynamic Epistemic Friction in Dialogue

arXiv: https://arxiv.org/abs/2506.10934 · HTML: https://mlsanity.com/paper/2506.10934/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 12 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Human values and AI feedback alignment](https://mlsanity.com/alignment/human-values-and-ai-feedback-alignment/)

## Builds on (most cited first, 15 of 15)

- [How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings](https://mlsanity.com/paper/1909.00512/) (2019)
- [A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations](https://mlsanity.com/paper/2111.06077/) (2021)
- [A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges](https://mlsanity.com/paper/2112.15424/) (2021)
- [Distributional Semantics and Linguistic Theory](https://mlsanity.com/paper/1905.01896/) (2019)
- [Linguistic Harbingers of Betrayal: A Case Study on an Online Strategy Game](https://mlsanity.com/paper/1506.04744/) (2015)
- [Epistemic Graphs for Representing and Reasoning with Positive and Negative Influences of Arguments](https://mlsanity.com/paper/1802.07489/) (2018)
- [Common Ground Tracking in Multimodal Dialogue](https://mlsanity.com/paper/2403.17284/) (2024)
- [Frictional Agent Alignment Framework: Slow Down and Don't Break Things](https://mlsanity.com/paper/2505.19428/) (2025)
- [Exploring a Behavioral Model of "Positive Friction" in Human-AI Interaction](https://mlsanity.com/paper/2402.09683/) (2024)
- [More Victories, Less Cooperation: Assessing Cicero's Diplomacy Play](https://mlsanity.com/paper/2406.04643/) (2024)
- [TRACE: Real-Time Multimodal Common Ground Tracking in Situated Collaborative Dialogues](https://mlsanity.com/paper/2503.09511/) (2025)
- [Emergence of hierarchical reference systems in multi-agent communication](https://mlsanity.com/paper/2203.13176/) (2022)
- [Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems](https://mlsanity.com/paper/2501.17348/) (2025)
- [A Formal Analysis of Multimodal Referring Strategies Under Common Ground](https://mlsanity.com/paper/2003.07385/) (2020)
- [AxomiyaBERTa: A Phonologically-aware Transformer Model for Assamese](https://mlsanity.com/paper/2305.13641/) (2023)

## Built on by (most cited first, 4 of 4)

- [Schema for In-Context Learning](https://mlsanity.com/paper/2510.13905/) (2025)
- [Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations](https://mlsanity.com/paper/2605.14175/) (2026)
- [Learning "Partner-Aware" Collaborators in Multi-Party Collaboration](https://mlsanity.com/paper/2510.22462/) (2025)
- [Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment](https://mlsanity.com/paper/2604.25136/) (2026)

## Abstract (arXiv)

Recent developments in aligning Large Language Models (LLMs) with human preferences have significantly enhanced their utility in human-AI collaborative scenarios. However, such approaches often neglect the critical role of "epistemic friction," or the inherent resistance encountered when updating beliefs in response to new, conflicting, or ambiguous information. In this paper, we define dynamic epistemic friction as the resistance to epistemic integration, characterized by the misalignment between an agent's current belief state and new propositions supported by external evidence. We position this within the framework of Dynamic Epistemic Logic (Van Benthem and Pacuit, 2011), where friction emerges as nontrivial belief-revision during the interaction. We then present analyses from a situated collaborative task that demonstrate how this model of epistemic friction can effectively predict belief updates in dialogues, and we subsequently discuss how the model of belief alignment as a measure of epistemic resistance or friction can naturally be made more sophisticated to accommodate the complexities of real-world dialogue scenarios.