When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis
For policymakers and researchers using LLMs to categorize public comments, this work highlights the need for disagreement-based evaluation as a complement to accuracy metrics.
Standard stance accuracy metrics for LLM evaluation in public comment analysis fail to detect when different models produce materially different categorizations. The proposed Interpretive Audit Pipeline uses multi-model disagreement to direct human review, revealing that inter-model divergence exceeds within-model prompt variation and that expert rubrics suppress deep disagreement.
Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes what policymakers see and which arguments register. Standard evaluation, anchored on stance accuracy against a small validated set, cannot detect when different models produce materially different categorizations of the same public input. We propose an Interpretive Audit Pipeline that treats multi-model disagreement as diagnostic of interpretive complexity and directs human review toward genuinely ambiguous public input. Analyzing 1,260 public comments on a federal USDA docket across four LLMs, we find that inter-model thematic divergence exceeds within-model prompt variation, and that an expert rubric suppresses deep interpretive disagreement without resolving it. In a two-stage labeling study on a stratified 40-comment subsample, four LLMs and a human annotator labeled independently and then revised after seeing the others' labels. Revision behavior varied across labelers, and the human annotator's revisions frequently introduced framings absent from the ensemble's collective output. We argue disagreement-based evaluation is a necessary complement to accuracy metrics for LLM-assisted interpretive coding.