ResearchCube provides a 3D spatial interface with bipolar trade-off dimensions and direct-manipulation interactions to support multi-dimensional research ideation, shown helpful in a study with 11 researchers for externalizing thinking and increasing agency.
hub Mixed citations
Homogenization effects of large language models on human creative ideation
Mixed citation behavior. Most common role is background (56%).
14
Pith papers citing it
Background
56% of classified citations
hub tools
citation-role summary
background 8
other 1
citation-polarity summary
representative citing papers
NIRVANA supplies keystroke-level logs, complete ChatGPT dialogues, and copied content from 77 students to reconstruct AI-assisted essay writing and classify students into four behavioral profiles: Lead Authors, Collaborators, Drafters, and Vibe Writers.
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
LLM originality raters exhibit self-preference bias toward artificial responses that disappears after controlling for idea elaboration in the Alternate Uses Task.
AI support during drafting decreases writing ownership more than during planning due to greater AI text and idea contributions, while improving essay quality.
A qualitative study with 22 creative writers finds that the reflective value of AI refusals depends on alignment with users' situational thinking phases, cognitive beliefs, and views of AI roles.
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
LLM assistance shortens idea-generation periods and reduces creative moments during programming tasks while yielding solutions with comparable idea counts and greater functional correctness.
A new toolkit with cards and maps enables AI designers to juxtapose values and harms in early concept stages, shown valuable in designer surveys and interviews.
Designers using generative AI for concept envisioning engage in reciprocal reflection-in-action that surfaces multi-level value tensions and prioritizes harm recognition over positive value articulation.
Generative AI needs conditional, context-specific opt-in consent at inference time rather than blanket training-time consent to handle real-world rights and usage complexities.
An online study of 70 students found that gender, race, and self-efficacy predict distinct ChatGPT query patterns during essay writing, with patterns linked to enjoyment and perceived ownership of the final essay.
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.
citing papers explorer
-
ResearchCube: Multi-Dimensional Trade-off Exploration for Research Ideation
ResearchCube provides a 3D spatial interface with bipolar trade-off dimensions and direct-manipulation interactions to support multi-dimensional research ideation, shown helpful in a study with 11 researchers for externalizing thinking and increasing agency.
-
NIRVANA: A Comprehensive Dataset for Reproducing How Students Use Generative AI for Essay Writing
NIRVANA supplies keystroke-level logs, complete ChatGPT dialogues, and copied content from 77 students to reconstruct AI-assisted essay writing and classify students into four behavioral profiles: Lead Authors, Collaborators, Drafters, and Vibe Writers.
-
Unlocking LLM Creativity in Science through Analogical Reasoning
Analogical reasoning increases LLM solution diversity by 90-173% and novelty rate to over 50%, delivering up to 13-fold gains on biomedical tasks including perturbation prediction and cell communication.
-
The Effect of Idea Elaboration on the Automatic Assessment of Idea Originality
LLM originality raters exhibit self-preference bias toward artificial responses that disappears after controlling for idea elaboration in the Alternate Uses Task.
-
From Planning to Revision: How AI Writing Support at Different Stages Alters Ownership
AI support during drafting decreases writing ownership more than during planning due to greater AI text and idea contributions, while improving essay quality.
-
Beyond Compliance: How AI Could Help Creative Writers by Refusing Them
A qualitative study with 22 creative writers finds that the reflective value of AI refusals depends on alignment with users' situational thinking phases, cognitive beliefs, and views of AI roles.
-
"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction
Concurrent human-agent interactions occur in 31.8% of turns and follow five action patterns explained by six triggers and four enabling factors, enabled by a context-aware design probe called CLEO.
-
Towards an AI co-scientist
A multi-agent AI system generates novel biomedical hypotheses that show promising experimental validation in drug repurposing for leukemia, new targets for liver fibrosis, and a bacterial gene transfer mechanism.
-
"Like Taking the Path of Least Resistance": Exploring the Impact of LLM Interaction on the Creative Process of Programming
LLM assistance shortens idea-generation periods and reduces creative moments during programming tasks while yielding solutions with comparable idea counts and greater functional correctness.
-
Developing an AI Concept Envisioning Toolkit to Support Reflective Juxtaposition of Values and Harms
A new toolkit with cards and maps enables AI designers to juxtapose values and harms in early concept stages, shown valuable in designer surveys and interviews.
-
How Designers Envision Value-Oriented AI Design Concepts with Generative AI
Designers using generative AI for concept envisioning engage in reciprocal reflection-in-action that surfaces multi-level value tensions and prioritizes harm recognition over positive value articulation.
-
Yes, But Not Always. Generative AI Needs Nuanced Opt-in
Generative AI needs conditional, context-specific opt-in consent at inference time rather than blanket training-time consent to handle real-world rights and usage complexities.
-
An Empirical Study to Understand How Students Use ChatGPT for Writing Essays
An online study of 70 students found that gender, race, and self-efficacy predict distinct ChatGPT query patterns during essay writing, with patterns linked to enjoyment and perceived ownership of the final essay.
-
Framing an AI with Values Reduces AI Reliance in AI-supported Writing Tasks
An online experiment finds that showing users an overview of an AI's values reduces reliance on AI suggestions during writing tasks.