@inproceedings{xie-etal-2026-cast,
    title = "{CAST}: Achieving Stable {LLM}-based Text Analysis for Data Analytics",
    author = "Xie, Jinxiang  and
      Li, Zihao  and
      He, Wei  and
      Ding, Rui  and
      Han, Shi  and
      Zhang, Dongmei",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.113/",
    pages = "2401--2420",
    ISBN = "979-8-89176-395-1",
    abstract = "Text analysis of tabular data relies on two core operations: \textit{summarization} for corpus-level theme extraction and \textit{tagging} for row-level labeling. A critical limitation of employing large language models (LLMs) for these tasks is their inability to meet the high standards of output stability demanded by data analytics. To address this challenge, we introduce \textbf{CAST} (\textbf{C}onsistency via \textbf{A}lgorithmic Prompting and \textbf{S}table \textbf{T}hinking), a framework that enhances output stability by constraining the model{'}s latent reasoning trajectory. CAST combines (i) Algorithmic Prompting to impose a procedural scaffold over valid reasoning transitions and (ii) Thinking-before-Speaking to enforce explicit intermediate commitments before final generation. To measure progress, we introduce \textbf{CAST-S} and \textbf{CAST-T}, stability metrics for bulleted summarization and tagging, and validate their alignment with human judgments. Experiments across publicly available benchmarks on multiple LLM backbones show that CAST consistently achieves the best stability among all baselines, improving Stability Score by up to 16.2{\%}, while maintaining or improving output quality."
}