Abstract
Large-scale text annotation brings expert insight to millions of documents, often through a codebook that AI annotators follow. Developing a robust codebook, however, takes months. Large language models (LLMs) could speed this process by applying an early codebook to the data, surfacing cases with strong LLM disagreement, and eliciting expert feedback to address them. We examined three ways experts can provide feedback for LLM codebook revision: (i) editing LLM-generated revisions driven by cross-LLM disagreement (Codebook Verifying), (ii) answering questions about LLM disagreements (Question Answering), and (iii) labeling disagreement cases with rationales (Rationale Labeling). Experiments on thousands of tutoring-session transcripts show that Rationale Labeling yielded the highest LLM-labeling accuracy (64.9%) against expert labels, outperforming the expert-revised codebook (57.8%). The best Question Answering setting also outperformed it (60.5%). Our work shows that LLMs can be used to strategically target expert attention, shortening months of codebook revision to days without sacrificing labeling performance.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
He, Z., Zhou, Z., Vanacore, K., Kizilcec, R. F., & Huang, T. H. '. (2026). Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation. https://omanscience.com/en/articles/experts-rise-where-llms-disagree-using-cross-model-disagreement-to-target-expert-effort-in-llm-codebook-revision-for-large-scale-annotation
MLA 9
He, Zeyu, et al. "Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation." https://omanscience.com/en/articles/experts-rise-where-llms-disagree-using-cross-model-disagreement-to-target-expert-effort-in-llm-codebook-revision-for-large-scale-annotation.
Chicago (author–date)
He, Zeyu, Zhuqian Zhou, Kirk Vanacore, Rene F. Kizilcec, and Ting-Hao 'Kenneth' Huang. 2026. "Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation." https://omanscience.com/en/articles/experts-rise-where-llms-disagree-using-cross-model-disagreement-to-target-expert-effort-in-llm-codebook-revision-for-large-scale-annotation.
Harvard
He, Z., Zhou, Z., Vanacore, K., Kizilcec, R. F. and Huang, T. H. '. (2026) 'Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation', Available at: https://omanscience.com/en/articles/experts-rise-where-llms-disagree-using-cross-model-disagreement-to-target-expert-effort-in-llm-codebook-revision-for-large-scale-annotation.
Vancouver
He Z, Zhou Z, Vanacore K, Kizilcec RF, Huang TH'. Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation. https://omanscience.com/en/articles/experts-rise-where-llms-disagree-using-cross-model-disagreement-to-target-expert-effort-in-llm-codebook-revision-for-large-scale-annotation
IEEE
Z. He, Z. Zhou, K. Vanacore, R. F. Kizilcec, and T. H. '. Huang, "Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation," https://omanscience.com/en/articles/experts-rise-where-llms-disagree-using-cross-model-disagreement-to-target-expert-effort-in-llm-codebook-revision-for-large-scale-annotation.