# Experts Rise Where LLMs Disagree: Using Cross-Model Disagreement to Target Expert Effort in LLM Codebook Revision for Large-Scale Annotation

arXiv: https://arxiv.org/abs/2609.26926 · HTML: https://mlsanity.com/paper/2609.26926/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 45 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [ChatGPT Outperforms Crowd-Workers for Text-Annotation Tasks](https://mlsanity.com/paper/2303.15056/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [Supporting Qualitative Analysis with Large Language Models: Combining Codebook with GPT-3 for Deductive Coding](https://mlsanity.com/paper/2304.10548/) (2023)
- [If in a Crowdsourced Data Annotation Pipeline, a GPT-4](https://mlsanity.com/paper/2402.16795/) (2024)
- [Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts](https://mlsanity.com/paper/2407.10747/) (2024)
- [Learning from Crowds with Crowd-Kit](https://mlsanity.com/paper/2109.08584/) (2021)
- [Prompting in the Dark: Assessing Human Performance in Prompt Engineering for Data Labeling When Gold Labels Are Absent](https://mlsanity.com/paper/2502.11267/) (2025)
- [PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues](https://mlsanity.com/paper/2505.16931/) (2025)
- [Are You There God? Lightweight Narrative Annotation of Christian Fiction with LMs](https://mlsanity.com/paper/2507.19756/) (2025)
- [CAPC-CG: A Large-Scale, Expert-Directed LLM-Annotated Corpus of Adaptive Policy Communication in China](https://mlsanity.com/paper/2510.08986/) (2025)

## Abstract (arXiv)

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.