Salvato in:
Dettagli Bibliografici
Autori principali: Jeyaganthan, Athikash, Xu, Kai, Becker, Franziska, Koch, Steffen
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.19309
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918459526348800
author Jeyaganthan, Athikash
Xu, Kai
Becker, Franziska
Koch, Steffen
author_facet Jeyaganthan, Athikash
Xu, Kai
Becker, Franziska
Koch, Steffen
contents Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes often shift (temporal drift), reducing the credibility of the analysis. Existing Computer-Assisted Qualitative Data Analysis (CAQDAS) tools provide support for data management but offer no workflow for real-time detection of these drifts. We present Co-Refine, an AI-augmented qualitative coding platform that delivers continuous, grounded feedback on coding consistency without disrupting the researcher's workflow. The system employs a three-stage audit pipeline: Stage 1 computes deterministic embedding-based metrics for mathematical consistency; Stage 2 grounds LLM verdicts within $\pm0.15$ of the deterministic scores; and Stage 3 produces code definitions from previous patterns to create a deepening feedback loop. Co-Refine demonstrates that deterministic scoring can effectively constrain LLM outputs to produce reliable, real-time audit signals for qualitative analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2604_19309
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Co-Refine: AI-Powered Tool Supporting Qualitative Analysis
Jeyaganthan, Athikash
Xu, Kai
Becker, Franziska
Koch, Steffen
Human-Computer Interaction
Artificial Intelligence
H.5.2; I.2.7
Qualitative coding relies on a researcher's application of codes to textual data. As coding proceeds across large datasets, interpretations of codes often shift (temporal drift), reducing the credibility of the analysis. Existing Computer-Assisted Qualitative Data Analysis (CAQDAS) tools provide support for data management but offer no workflow for real-time detection of these drifts. We present Co-Refine, an AI-augmented qualitative coding platform that delivers continuous, grounded feedback on coding consistency without disrupting the researcher's workflow. The system employs a three-stage audit pipeline: Stage 1 computes deterministic embedding-based metrics for mathematical consistency; Stage 2 grounds LLM verdicts within $\pm0.15$ of the deterministic scores; and Stage 3 produces code definitions from previous patterns to create a deepening feedback loop. Co-Refine demonstrates that deterministic scoring can effectively constrain LLM outputs to produce reliable, real-time audit signals for qualitative analysis.
title Co-Refine: AI-Powered Tool Supporting Qualitative Analysis
topic Human-Computer Interaction
Artificial Intelligence
H.5.2; I.2.7
url https://arxiv.org/abs/2604.19309