Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.04735 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911569589305344 |
|---|---|
| author | Li, Zhu Qu, Jiaming Chang, Yuan |
| author_facet | Li, Zhu Qu, Jiaming Chang, Yuan |
| contents | Large language models (LLMs) are increasingly acting as collaborative writing partners, raising questions about their impact on human agency. In this exploratory work, we investigate five "dark patterns" in human-AI co-creativity -- subtle model behaviors that can suppress or distort the creative process: Sycophancy, Tone Policing, Moralizing, Loop of Death, and Anchoring. Through a series of controlled sessions where LLMs are prompted as writing assistants across diverse literary forms and themes, we analyze the prevalence of these behaviors in generated responses. Our preliminary results suggest that Sycophancy is nearly ubiquitous (91.7% of cases), particularly in sensitive topics, while Anchoring appears to be dependent on literary forms, surfacing most frequently in folktales. This study indicates that these dark patterns, often byproducts of safety alignment, may inadvertently narrow creative exploration and proposes design considerations for AI systems that effectively support creative writing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04735 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Lighting Up or Dimming Down? Exploring Dark Patterns of LLMs in Co-Creativity Li, Zhu Qu, Jiaming Chang, Yuan Computation and Language Large language models (LLMs) are increasingly acting as collaborative writing partners, raising questions about their impact on human agency. In this exploratory work, we investigate five "dark patterns" in human-AI co-creativity -- subtle model behaviors that can suppress or distort the creative process: Sycophancy, Tone Policing, Moralizing, Loop of Death, and Anchoring. Through a series of controlled sessions where LLMs are prompted as writing assistants across diverse literary forms and themes, we analyze the prevalence of these behaviors in generated responses. Our preliminary results suggest that Sycophancy is nearly ubiquitous (91.7% of cases), particularly in sensitive topics, while Anchoring appears to be dependent on literary forms, surfacing most frequently in folktales. This study indicates that these dark patterns, often byproducts of safety alignment, may inadvertently narrow creative exploration and proposes design considerations for AI systems that effectively support creative writing. |
| title | Lighting Up or Dimming Down? Exploring Dark Patterns of LLMs in Co-Creativity |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.04735 |