# Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems

arXiv: https://arxiv.org/abs/2501.17348 · HTML: https://mlsanity.com/paper/2501.17348/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jan 2025.

## Built on by (most cited first, 7 of 7)

- [Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes](https://mlsanity.com/paper/2509.05882/) (2025)
- [Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat Logs](https://mlsanity.com/paper/2503.12370/) (2025)
- [Dynamic Epistemic Friction in Dialogue](https://mlsanity.com/paper/2506.10934/) (2025)
- [From Task Success to Productive Success: Evaluating Human-AI Collaboration by Quality and Cost](https://mlsanity.com/paper/2609.21117/) (2026)
- [Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts](https://mlsanity.com/paper/2604.02713/) (2026)
- [It Matters How You Say It: Exploring Rhetorical Patterns for AI-Assisted Information Evaluation](https://mlsanity.com/paper/2607.17627/) (2026)
- [Illusion of Alignment: Detecting Hidden Disagreement in Collaborative Dialogue](https://mlsanity.com/paper/2608.08210/) (2026)

## Abstract (arXiv)

While theories of discourse and cognitive science have long recognized the value of unhurried pacing, recent dialogue research tends to minimize friction in conversational systems. Yet, frictionless dialogue risks fostering uncritical reliance on AI outputs, which can obscure implicit assumptions and lead to unintended consequences. To meet this challenge, we propose integrating positive friction into conversational AI, which promotes user reflection on goals, critical thinking on system response, and subsequent re-conditioning of AI systems. We hypothesize systems can improve goal alignment, modeling of user mental states, and task success by deliberately slowing down conversations in strategic moments to ask questions, reveal assumptions, or pause. We present an ontology of positive friction and collect expert human annotations on multi-domain and embodied goal-oriented corpora. Experiments on these corpora, along with simulated interactions using state-of-the-art systems, suggest incorporating friction not only fosters accountable decision-making, but also enhances machine understanding of user beliefs and goals, and increases task success rates.