@inproceedings{feng-etal-2025-sportreason,
title = "{S}port{R}eason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering",
author = "Feng, Kaiyue and
Zhang, Siyue and
Chen, Bingsen and
Zhao, Yilun and
Zhao, Chen",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.34/",
pages = "649--662",
ISBN = "979-8-89176-332-6",
abstract = "We present SportReason, a benchmark for retrieval-augmented reasoning on numerical sports questions. Unlike existing benchmarks limited to one or two evidence units, SportReason requires combining and reasoning across free-text, structured tables, and semi-structured infoboxes. We provide 3,000 human-verified QA pairs by repurposing existing QA and table generation datasets, and by prompting large language models (LLMs). Each pair is grounded in multiple evidence from a multi-modal Wikipedia corpus containing 200K knowledge contexts. We evaluate existing retrievers and rerankers, along with agentic Retrieval-Augmented Generation (RAG) systems. The experimental results show that multi-evidence retrieval remains a challenge. Agentic RAG systems (e.g., Search-o1), despite iterative retrieval and reasoning capabilities, fail to improve performance due to imprecise queries, simple training, and distracting information."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2025-sportreason">
<titleInfo>
<title>SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kaiyue</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siyue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingsen</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>We present SportReason, a benchmark for retrieval-augmented reasoning on numerical sports questions. Unlike existing benchmarks limited to one or two evidence units, SportReason requires combining and reasoning across free-text, structured tables, and semi-structured infoboxes. We provide 3,000 human-verified QA pairs by repurposing existing QA and table generation datasets, and by prompting large language models (LLMs). Each pair is grounded in multiple evidence from a multi-modal Wikipedia corpus containing 200K knowledge contexts. We evaluate existing retrievers and rerankers, along with agentic Retrieval-Augmented Generation (RAG) systems. The experimental results show that multi-evidence retrieval remains a challenge. Agentic RAG systems (e.g., Search-o1), despite iterative retrieval and reasoning capabilities, fail to improve performance due to imprecise queries, simple training, and distracting information.</abstract>
<identifier type="citekey">feng-etal-2025-sportreason</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.34/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>649</start>
<end>662</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering
%A Feng, Kaiyue
%A Zhang, Siyue
%A Chen, Bingsen
%A Zhao, Yilun
%A Zhao, Chen
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F feng-etal-2025-sportreason
%X We present SportReason, a benchmark for retrieval-augmented reasoning on numerical sports questions. Unlike existing benchmarks limited to one or two evidence units, SportReason requires combining and reasoning across free-text, structured tables, and semi-structured infoboxes. We provide 3,000 human-verified QA pairs by repurposing existing QA and table generation datasets, and by prompting large language models (LLMs). Each pair is grounded in multiple evidence from a multi-modal Wikipedia corpus containing 200K knowledge contexts. We evaluate existing retrievers and rerankers, along with agentic Retrieval-Augmented Generation (RAG) systems. The experimental results show that multi-evidence retrieval remains a challenge. Agentic RAG systems (e.g., Search-o1), despite iterative retrieval and reasoning capabilities, fail to improve performance due to imprecise queries, simple training, and distracting information.
%U https://aclanthology.org/2025.emnlp-main.34/
%P 649-662
Markdown (Informal)
[SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answering](https://aclanthology.org/2025.emnlp-main.34/) (Feng et al., EMNLP 2025)
ACL