Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916805032804352 |
|---|---|
| author | Mysore, Sheshera Das, Debarati Cao, Hancheng Sarrafzadeh, Bahareh |
| author_facet | Mysore, Sheshera Das, Debarati Cao, Hancheng Sarrafzadeh, Bahareh |
| contents | As large language models (LLMs) are used in complex writing workflows, users engage in multi-turn interactions to steer generations to better fit their needs. Rather than passively accepting output, users actively refine, explore, and co-construct text. We conduct a large-scale analysis of this collaborative behavior for users engaged in writing tasks in the wild with two popular AI assistants, Bing Copilot and WildChat. Our analysis goes beyond simple task classification or satisfaction estimation common in prior work and instead characterizes how users interact with LLMs through the course of a session. We identify prototypical behaviors in how users interact with LLMs in prompts following their original request. We refer to these as Prototypical Human-AI Collaboration Behaviors (PATHs) and find that a small group of PATHs explain a majority of the variation seen in user-LLM interaction. These PATHs span users revising intents, exploring texts, posing questions, adjusting style or injecting new content. Next, we find statistically significant correlations between specific writing intents and PATHs, revealing how users' intents shape their collaboration behaviors. We conclude by discussing the implications of our findings on LLM alignment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_16023 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild Mysore, Sheshera Das, Debarati Cao, Hancheng Sarrafzadeh, Bahareh Computation and Language Human-Computer Interaction As large language models (LLMs) are used in complex writing workflows, users engage in multi-turn interactions to steer generations to better fit their needs. Rather than passively accepting output, users actively refine, explore, and co-construct text. We conduct a large-scale analysis of this collaborative behavior for users engaged in writing tasks in the wild with two popular AI assistants, Bing Copilot and WildChat. Our analysis goes beyond simple task classification or satisfaction estimation common in prior work and instead characterizes how users interact with LLMs through the course of a session. We identify prototypical behaviors in how users interact with LLMs in prompts following their original request. We refer to these as Prototypical Human-AI Collaboration Behaviors (PATHs) and find that a small group of PATHs explain a majority of the variation seen in user-LLM interaction. These PATHs span users revising intents, exploring texts, posing questions, adjusting style or injecting new content. Next, we find statistically significant correlations between specific writing intents and PATHs, revealing how users' intents shape their collaboration behaviors. We conclude by discussing the implications of our findings on LLM alignment. |
| title | Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wild |
| topic | Computation and Language Human-Computer Interaction |
| url | https://arxiv.org/abs/2505.16023 |