cs.AINov 6, 2026

When F1 Is Not Enough: Auditing Codebooks for LLM-Assisted Annotation

Authors: Yuehong Cassandra Tai, Qunhua Li

Organizations: Center for Social Data Analytics, Pennsylvania State University, United States · Department of Statistics, Pennsylvania State University, United States

Abstract

Large language models (LLMs) are increasingly used for text annotation in social science, but standard performance metrics do not explain why errors occur. Low F1 may reflect limitations of the annotation system, defects in the written codebook, or inconsistency in reference labels. We propose a pre-deployment codebook audit for LLM-assisted annotation. The audit uses class-specific metrics and confusion matrices to identify problematic classes and boundaries, structured document-level review to attribute error sources, and targeted codebook revision followed by held-out evaluation. We apply the audit to two published multi-class codebooks from distinct domains. In both applications, the audit identifies under-specified or conflicting coding rules, and targeted revisions reduce the diagnosed errors on held-out data. Analyses with two LLM annotators show that some problematic boundaries and codebook revisions transfer across models, whereas other revision effects are annotator-specific. The results show that LLM annotation errors can help identify weaknesses in the written measurement instrument, not only in the model. Codebook auditing complements prompting, retrieval, and fine-tuning by clarifying whether persistent errors call for model improvement, codebook revision, or renewed scrutiny of reference labels.

Figures & tables

Appendix figures & tables31 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Sep 22, 2026

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

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.
Oct 26, 2026

High Scores, Hidden Failures: Evaluating Codebook-Based LLM Content Analysis

Large language models (LLMs) are increasingly used for codebook-based content analysis in computational social science, where codebooks translate theoretical concepts into labeling schemes. While prior work reports strong predictive performance, it remains unclear whether these systems produce reliable and robust text annotations. We conduct a large-scale empirical failure-mode analysis of LLM-based coding pipelines across four datasets and five models by systematically evaluating their stability, robustness, and conceptual validity under controlled perturbations, domain shifts, and optimization procedures. We uncover multiple failure modes that are largely invisible under standard metrics, showing that high aggregate scores frequently coexist with severe label-level disparities, instability across runs, domain sensitivity, and shifts in label interpretation. Importantly, these failure modes persist under widely used optimization strategies and remain largely invisible under standard metrics such as accuracy and micro-F1. Our results demonstrate that current LLM-based coding pipelines cannot be treated as stable measurement tools without targeted validation beyond aggregate performance.
Aug 24, 2026

Observational Equivalence of LLM and Human Annotation

In this paper, we show that humans and large language models (LLMs) are observationally equivalent in coding texts. Recent LLMs agree with attentive humans at rates comparable to those observed among humans, and cross-LLM disagreement concentrates on texts that also divide humans. We demonstrate these patterns through replications of text-classification tasks from 14 peer-reviewed political science studies, with 13 LLMs, three human coders (Ph.D. students), and 165 crowd coders, independently applying identical codebooks. We further find that clarifying an underspecified codebook increases agreement among humans and between humans and LLMs. Together, these findings point to ambiguity in texts and coding rules as a shared source of disagreement and challenge the presumption that human labels should take precedence whenever humans and LLMs differ. We therefore argue that the central challenge of text annotation is not simply choosing between humans and LLMs, but developing coding rules that minimize ambiguity and accounting for the ambiguity that remains. To this end, we propose using cross-LLM disagreement to identify difficult cases, guide human review, and refine codebooks, and we develop ambiguity-aware bounds for downstream inference without requiring ground truth for every text.