Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.23535 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917523814875136 |
|---|---|
| author | Fang, Youqing Tang, Yinhao Sun, Yanan Liu, Jiangning Wang, Ziyi Zhao, Xun Liu, Bin Zhang, Weiming Liu, Kuikun Zhang, Wenwei Chen, Kai |
| author_facet | Fang, Youqing Tang, Yinhao Sun, Yanan Liu, Jiangning Wang, Ziyi Zhao, Xun Liu, Bin Zhang, Weiming Liu, Kuikun Zhang, Wenwei Chen, Kai |
| contents | Recent writing assistants are increasingly shifting from passive, prompt-driven interaction to proactive, suggestion-based completion, which integrates localized continuations into the writing flow and reduces coordination burden. However, existing evaluations simply focus on output quality, failing to capture how users accept, edit, or repair suggestions in real-time interaction, and thus obscuring the true usability of proactive co-writing systems. To address this gap, we adopt a sequential, behavior-centered view of interactive writing and formalize co-writing as a Human-in-the-Loop Markov Decision Process, modeling writing as an interaction shaped by user acceptance and editing decisions. Based on this formulation, we introduce the Co-Writing Fidelity Suite, an interaction-aware metric suite that captures both user-assistant alignment and cognitive editing effort, including Hierarchical Acceptance Rate and Knowledge-aware Editing Distance. We conduct a large-scale simulation study across 16 writing domains, using 1,688 controlled continuation queries sampled from different writing stages. Our analysis reveals systematic effects of interaction structure on acceptance behavior and editing cost. A follow-up user study with 30 participants confirms that these behavioral patterns align with real user experience. Together, our findings demonstrate that interaction-aware evaluation provides insights beyond output-only metrics and informs the design of more effective proactive writing assistants. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_23535 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MindCopilot: Towards Formalizing and Evaluating Granular Human-LLM Co-Writing Fang, Youqing Tang, Yinhao Sun, Yanan Liu, Jiangning Wang, Ziyi Zhao, Xun Liu, Bin Zhang, Weiming Liu, Kuikun Zhang, Wenwei Chen, Kai Human-Computer Interaction Recent writing assistants are increasingly shifting from passive, prompt-driven interaction to proactive, suggestion-based completion, which integrates localized continuations into the writing flow and reduces coordination burden. However, existing evaluations simply focus on output quality, failing to capture how users accept, edit, or repair suggestions in real-time interaction, and thus obscuring the true usability of proactive co-writing systems. To address this gap, we adopt a sequential, behavior-centered view of interactive writing and formalize co-writing as a Human-in-the-Loop Markov Decision Process, modeling writing as an interaction shaped by user acceptance and editing decisions. Based on this formulation, we introduce the Co-Writing Fidelity Suite, an interaction-aware metric suite that captures both user-assistant alignment and cognitive editing effort, including Hierarchical Acceptance Rate and Knowledge-aware Editing Distance. We conduct a large-scale simulation study across 16 writing domains, using 1,688 controlled continuation queries sampled from different writing stages. Our analysis reveals systematic effects of interaction structure on acceptance behavior and editing cost. A follow-up user study with 30 participants confirms that these behavioral patterns align with real user experience. Together, our findings demonstrate that interaction-aware evaluation provides insights beyond output-only metrics and informs the design of more effective proactive writing assistants. |
| title | MindCopilot: Towards Formalizing and Evaluating Granular Human-LLM Co-Writing |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2605.23535 |