# How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding

arXiv: https://arxiv.org/abs/2609.11109 · HTML: https://mlsanity.com/paper/2609.11109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 39 of its 162 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 30 of 39)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Learning Loss for Active Learning](https://mlsanity.com/paper/1905.03677/) (2019)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View](https://mlsanity.com/paper/2310.02124/) (2023)
- [Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?](https://mlsanity.com/paper/2402.18272/) (2024)
- [Homogenization Effects of Large Language Models on Human Creative Ideation](https://mlsanity.com/paper/2402.01536/) (2024)
- [Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs](https://mlsanity.com/paper/2311.17371/) (2023)
- [Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding](https://mlsanity.com/paper/2304.10548/) (2023)
- [Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights Cases](https://mlsanity.com/paper/2103.13084/) (2021)
- [LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis](https://mlsanity.com/paper/2310.15100/) (2023)
- [LLM-Assisted Content Analysis: Using Large Language Models to Support Deductive Coding](https://mlsanity.com/paper/2306.14924/) (2023)
- [Personas as a Way to Model Truthfulness in Language Models](https://mlsanity.com/paper/2310.18168/) (2023)
- [Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches](https://mlsanity.com/paper/2211.16285/) (2022)
- [CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models](https://mlsanity.com/paper/2304.07366/) (2023)
- [Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions](https://mlsanity.com/paper/1702.01119/) (2017)
- [Using AI Assistants in Software Development: A Qualitative Study on Security Practices and Concerns](https://mlsanity.com/paper/2405.06371/) (2024)
- [CoAIcoder: Examining the Effectiveness of AI-assisted Human-to-Human Collaboration in Qualitative Analysis](https://mlsanity.com/paper/2304.05560/) (2023)
- [Using Large Language Models for Qualitative Analysis can Introduce Serious Bias](https://mlsanity.com/paper/2309.17147/) (2023)
- [Scalable Qualitative Coding with LLMs: Chain-of-Thought Reasoning Matches Human Performance in Some Hermeneutic Tasks](https://mlsanity.com/paper/2401.15170/) (2024)
- [Redefining Qualitative Analysis in the AI Era: Utilizing ChatGPT for Efficient Thematic Analysis](https://mlsanity.com/paper/2309.10771/) (2023)
- [Can Large Language Models emulate an inductive Thematic Analysis of semi-structured interviews? An exploration and provocation on the limits of the approach and the model](https://mlsanity.com/paper/2305.13014/) (2023)
- [Automating Thematic Analysis: How LLMs Analyse Controversial Topics](https://mlsanity.com/paper/2405.06919/) (2024)
- [Text Alignment Is An Efficient Unified Model for Massive NLP Tasks](https://mlsanity.com/paper/2307.02729/) (2023)
- [QualiGPT: GPT as an easy-to-use tool for qualitative coding](https://mlsanity.com/paper/2310.07061/) (2023)
- [Harnessing ChatGPT for thematic analysis: Are we ready?](https://mlsanity.com/paper/2310.14545/) (2023)
- [QuaLLM: An LLM-based Framework to Extract Quantitative Insights from Online Forums](https://mlsanity.com/paper/2405.05345/) (2024)
- [Applications and Implications of Large Language Models in Qualitative Analysis: A New Frontier for Empirical Software Engineering](https://mlsanity.com/paper/2412.06564/) (2024)
- [Discourse Parsing of Contentious, Non-Convergent Online Discussions](https://mlsanity.com/paper/2012.04585/) (2020)
- ["Mama Always Had a Way of Explaining Things So I Could Understand'': A Dialogue Corpus for Learning to Construct Explanations](https://mlsanity.com/paper/2209.02508/) (2022)

## Abstract (arXiv)

The utility of AI in multi-coder qualitative coding has been widely discussed, yet little empirical evidence exists to delineate the contexts in which it performs reliably. We address this gap by quantifying the effectiveness of multi-agent LLM coding across varied qualitative datasets, revealing key contextual and structural factors that mediate coding outcomes. We developed a literature-informed baseline pipeline that enables AI agents to independently code, debate, and reconcile disagreements. Results revealed that coding accuracy depends on factors such as codebook length, qualitative data similarity, and agent disagreement. Notably, intense and unresolved debates between agents led to higher accuracy. Our analysis showed that while LLMs emulate many human discussion behaviors, they lack adaptive responsiveness to context. From these findings, we offer design recommendations for building automated coding systems. Our open-source AI discussion dataset and methodological framework lay the groundwork for advancing the design of AI-mediated automated thematic analysis.