@inproceedings{du-etal-2026-analyzing,
    title = "Analyzing {LLM} Instruction Optimization for Tabular Fact Verification",
    author = "Du, Xiaotang  and
      Hong, Giwon  and
      Kwan, Wai-Chung  and
      Saxena, Rohit  and
      Titov, Ivan  and
      Minervini, Pasquale  and
      Allaway, Emily",
    editor = "Demberg, Vera  and
      Inui, Kentaro  and
      Marquez, Llu{\'i}s",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EACL} 2026",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-eacl/2026.findings-eacl.161/",
    pages = "3078--3108",
    ISBN = "979-8-89176-386-9",
    abstract = "Instruction optimization provides a lightweight, model-agnostic approach to enhancing the reasoning performance of large language models (LLMs). This paper presents the first systematic comparison of instruction optimization, based on the DSPy optimization framework, for tabular fact verification. We evaluate four out-of-the-box prompting techniques that cover both text-only prompting and code use: direct prediction, Chain-of-Thought (CoT), ReAct with SQL tools, and CodeAct with Python execution. We study three optimizers from the DSPy framework{---}COPRO, MiPROv2, and SIMBA{---}across four benchmarks and three model families. We find that instruction optimization consistently improves verification accuracy, with MiPROv2 yielding the most stable gains for CoT, and SIMBA providing the largest benefits for ReAct agents, particularly at larger model scales. Behavioral analyses reveal that SIMBA encourages more direct reasoning paths by applying heuristics, thereby improving numerical comparison abilities in CoT reasoning and helping avoid unnecessary tool calls in ReAct agents. Across different prompting techniques, CoT remains effective for tabular fact checking, especially with smaller models. Although ReAct agents built with larger models can achieve competitive performance, they require careful instruction optimization."
}