# Computational KJ-Ho: An Analyst-Bias-Free Insight Extraction Framework from Large-Scale Qualitative Data Using Domain-Specialized LLMs

arXiv: https://arxiv.org/abs/2608.16467 · HTML: https://mlsanity.com/paper/2608.16467/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 73 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [Do Prompt-Based Models Really Understand the Meaning of their Prompts?](https://mlsanity.com/paper/2109.01247/) (2021)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task](https://mlsanity.com/paper/2004.14855/) (2020)
- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations](https://mlsanity.com/paper/2303.18027/) (2023)
- [CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models](https://mlsanity.com/paper/2304.07366/) (2023)
- [OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulation](https://mlsanity.com/paper/2506.05606/) (2025)
- [BASES: Large-scale Web Search User Simulation with Large Language Model based Agents](https://mlsanity.com/paper/2402.17505/) (2024)
- [HICode: Hierarchical Inductive Coding with LLMs](https://mlsanity.com/paper/2509.17946/) (2025)
- [A Computational Method for Measuring "Open Codes" in Qualitative Analysis](https://mlsanity.com/paper/2411.12142/) (2024)
- [LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research](https://mlsanity.com/paper/2509.24294/) (2025)
- [DeTAILS: Deep Thematic Analysis with Iterative LLM Support](https://mlsanity.com/paper/2510.17575/) (2025)
- [Stabilizing Reasoning in Medical LLMs with Continued Pretraining and Reasoning Preference Optimization](https://mlsanity.com/paper/2504.18080/) (2025)
- [Efficiency with Rigor! A Trustworthy LLM-powered Workflow for Qualitative Data Analysis](https://mlsanity.com/paper/2501.00775/) (2025)
- [Transforming the Voice of the Customer: Large Language Models for Identifying Customer Needs](https://mlsanity.com/paper/2503.01870/) (2025)
- [SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis](https://mlsanity.com/paper/2509.17167/) (2025)
- [A Framework For Discussing LLMs as Tools for Qualitative Analysis](https://mlsanity.com/paper/2407.11198/) (2024)
- [Neo-Grounded Theory: A Methodological Innovation Integrating High-Dimensional Vector Clustering and Multi-Agent Collaboration for Qualitative Research](https://mlsanity.com/paper/2509.25244/) (2025)

## Abstract (arXiv)

The qualitative research methodologies that underpin consumer-insight generation - the KJ method, Grounded Theory, and Thematic Analysis - share a structural constraint: the cognitive processing capacity of the human analyst. Replication research further shows that conclusions vary substantially across analysts analyzing identical data (analyst bias). This paper proposes Computational KJ-Ho (the Kawakita Jiro method), a theoretical framework that computationally realizes the KJ method's epistemology - letting structure emerge from the data itself without imposing the analyst's preconceptions - an orientation we term "analyst-bias-free." The framework employs a domain-specialized LLM built through continued pre-training (CPT) on a marketing-research corpus and supervised fine-tuning (SFT) on expert-curated insight pairs, organized as a three-layer architecture: data structuring, insight extraction, and strategy generation. Two preliminary studies in the Japanese marketing context support the necessity of CPT-based domain specialization. The paper makes five contributions: (1) a theoretical integration of the KJ method, Grounded Theory, and Peircean abduction into a single epistemological commitment of data-driven explanation generation; (2) a three-layer architecture leveraging domain-specialized embeddings for cross-interview analysis; (3) two novel evaluation metrics, InsightExtraction-F1 and MarketingQA; (4) explicit engagement with the WEIRD problem, centering a non-Western methodology; and (5) five practice-derived problem formulations from nearly three decades of marketing-research practice, translated into design requirements. The human analyst retains a supervisory role. This is a concept paper presented ahead of empirical validation.