@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://aclanthology.org/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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nair-yang-2025-treesearch">
<titleInfo>
<title>TreeSearch at SemEval-2025 Task 8: Monte Carlo Tree Search for Question-Answering over Tabular Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aakarsh</namePart>
<namePart type="family">Nair</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huixin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Rosenthal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-273-2</identifier>
</relatedItem>
<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.</abstract>
<identifier type="citekey">nair-yang-2025-treesearch</identifier>
<location>
<url>https://aclanthology.org/2025.semeval-1.256/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1974</start>
<end>1980</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TreeSearch at SemEval-2025 Task 8: Monte Carlo Tree Search for Question-Answering over Tabular Data
%A Nair, Aakarsh
%A Yang, Huixin
%Y Rosenthal, Sara
%Y Rosá, Aiala
%Y Ghosh, Debanjan
%Y Zampieri, Marcos
%S Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-273-2
%F nair-yang-2025-treesearch
%X 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.
%U https://aclanthology.org/2025.semeval-1.256/
%P 1974-1980
Markdown (Informal)
[TreeSearch at SemEval-2025 Task 8: Monte Carlo Tree Search for Question-Answering over Tabular Data](https://aclanthology.org/2025.semeval-1.256/) (Nair & Yang, SemEval 2025)
ACL