Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917907212009472 |
|---|---|
| author | İnan, Mert Sicilia, Anthony Dey, Suvodip Dongre, Vardhan Srinivasan, Tejas Thomason, Jesse Tür, Gökhan Hakkani-Tür, Dilek Alikhani, Malihe |
| author_facet | İnan, Mert Sicilia, Anthony Dey, Suvodip Dongre, Vardhan Srinivasan, Tejas Thomason, Jesse Tür, Gökhan Hakkani-Tür, Dilek Alikhani, Malihe |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17348 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems İnan, Mert Sicilia, Anthony Dey, Suvodip Dongre, Vardhan Srinivasan, Tejas Thomason, Jesse Tür, Gökhan Hakkani-Tür, Dilek Alikhani, Malihe Computation and Language Human-Computer Interaction 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. |
| title | Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2501.17348 |