Co-Refine combines deterministic embedding metrics with LLM feedback in a three-stage pipeline to detect temporal drift in qualitative coding without disrupting the workflow.
Glassman, and Toby Jia-Jun Li
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
A method merges codebooks via LLM and evaluates human and AI inductive coding with four new metrics on an online conversation dataset.
Mixed-methods study finds AI assistance linked to higher textual overlap with suggestions in writing tasks, and a reflective interface prototype increases user awareness of AI incorporation.
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.
citing papers explorer
-
Co-Refine: AI-Powered Tool Supporting Qualitative Analysis
Co-Refine combines deterministic embedding metrics with LLM feedback in a three-stage pipeline to detect temporal drift in qualitative coding without disrupting the workflow.
-
A Computational Method for Measuring "Open Codes" in Qualitative Analysis
A method merges codebooks via LLM and evaluates human and AI inductive coding with four new metrics on an online conversation dataset.
-
Overreliance in Writing Tasks: Exploring Similarity-Based Measures of AI Influence on Writing and Proposing a Reflective Writing Interface Intervention
Mixed-methods study finds AI assistance linked to higher textual overlap with suggestions in writing tasks, and a reflective interface prototype increases user awareness of AI incorporation.
-
Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics
Case studies with blind UK residents and people from Kerala and Tamil Nadu demonstrate that community input at the systematization stage produces culturally grounded definitions of appropriateness for text-to-image model outputs.