How AI Coders Discuss, Disagree, and Reach Consensus: Challenges and Opportunities for LLM-Based Qualitative Coding
This work developed a literature-informed baseline pipeline that enables AI agents to independently code, debate, and reconcile disagreements, and revealed that coding accuracy depends on factors such as codebook length, qualitative data similarity, and agent disagreement.
Jeongyeon Kim, John C. Mitchell
· 0 citations