Users Mispredict Their Own Preferences for AI Writing Assistance
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918277764087808 |
|---|---|
| author | Lai, Vivian Buçinca, Zana Akpinar, Nil-Jana Houtti, Mo Kang, Hyeonsu B. Chian, Kevin Suh, Namjoon Williams, Alex C. |
| author_facet | Lai, Vivian Buçinca, Zana Akpinar, Nil-Jana Houtti, Mo Kang, Hyeonsu B. Chian, Kevin Suh, Namjoon Williams, Alex C. |
| contents | Proactive AI writing assistants need to predict when users want drafting help, yet we lack empirical understanding of what drives preferences. Through a factorial vignette study with 50 participants making 750 pairwise comparisons, we find compositional effort dominates decisions ($ρ= 0.597$) while urgency shows no predictive power ($ρ\approx 0$). More critically, users exhibit a striking perception-behavior gap: they rank urgency first in self-reports despite it being the weakest behavioral driver, representing a complete preference inversion. This misalignment has measurable consequences. Systems designed from users' stated preferences achieve only 57.7\% accuracy, underperforming even naive baselines, while systems using behavioral patterns reach significantly higher 61.3\% ($p < 0.05$). These findings demonstrate that relying on user introspection for system design actively misleads optimization, with direct implications for proactive natural language generation (NLG) systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_04461 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Users Mispredict Their Own Preferences for AI Writing Assistance Lai, Vivian Buçinca, Zana Akpinar, Nil-Jana Houtti, Mo Kang, Hyeonsu B. Chian, Kevin Suh, Namjoon Williams, Alex C. Computation and Language Human-Computer Interaction Proactive AI writing assistants need to predict when users want drafting help, yet we lack empirical understanding of what drives preferences. Through a factorial vignette study with 50 participants making 750 pairwise comparisons, we find compositional effort dominates decisions ($ρ= 0.597$) while urgency shows no predictive power ($ρ\approx 0$). More critically, users exhibit a striking perception-behavior gap: they rank urgency first in self-reports despite it being the weakest behavioral driver, representing a complete preference inversion. This misalignment has measurable consequences. Systems designed from users' stated preferences achieve only 57.7\% accuracy, underperforming even naive baselines, while systems using behavioral patterns reach significantly higher 61.3\% ($p < 0.05$). These findings demonstrate that relying on user introspection for system design actively misleads optimization, with direct implications for proactive natural language generation (NLG) systems. |
| title | Users Mispredict Their Own Preferences for AI Writing Assistance |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2601.04461 |