@inproceedings{nair-yang-2025-treesearch,
    title = "{T}ree{S}earch at {S}em{E}val-2025 Task 8: {M}onte {C}arlo Tree Search for Question-Answering over Tabular Data",
    author = "Nair, Aakarsh  and
      Yang, Huixin",
    editor = "Rosenthal, Sara  and
      Ros{\'a}, Aiala  and
      Ghosh, Debanjan  and
      Zampieri, Marcos",
    booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2025-08/2025.semeval-1.256/",
    pages = "1974--1980",
    ISBN = "979-8-89176-273-2",
    abstract = "Large Language Models (LLMs) can answer diverse questions but often generate factually incorrect responses. SemEval-2025 Task 8 focuses on table-based question-answering, providing 65 real-world tabular datasets and 1,300 questions that require precise filtering and summarization of underlying tables.We approach this problem as a neuro-symbolic code generation task, translating natural language queries into executable Python code to ensure contextually relevant and factually accurate answers. We formulate LLM decoding as a Markov Decision Process, enabling Monte Carlo Tree Search (MCTS) as a lookahead-based planning algorithm while decoding from the underlying code-generating LLM, instead of standard beam search.Execution success on synthetic tests and real datasets serves as a reward signal, allowing MCTS to explore multiple code-generation paths, validate outcomes, assign value to partial solutions, and refine code iteratively rather than merely maximizing sequence likelihood in a single step. Our approach improves accuracy by 2.38x compared to standard decoding."
}