@inproceedings{upadhyay-etal-2026-q,
title = "{Q}-{STR}: Diagnosing Query-Driven Text-to-Table Reasoning in Cricket Narratives",
author = "Upadhyay, Ritam and
Ahuja, Naman and
Baral, Rishabh and
Garimella, Aparna and
Gupta, Vivek",
editor = "T.Y.S.S., Santosh and
Agarwal, Amit and
Gupta, Vivek and
Kementchedjhieva, Yova and
Garimella, Aparna and
Hou, Yufang",
booktitle = "The Proceedings of Workshop on Document Intelligence and Understanding",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.docinsights-1.15/",
pages = "196--216",
ISBN = "979-8-89176-477-4",
abstract = "Many analytical questions over long narratives are structured even when their source documents are not. Answering them requires identifying relevant events, inducing a query-specific schema, grounding records in dispersed evidence, and computing the values of an answer table. We introduce Q-STR, a cricket-domain benchmark and diagnostic for this query-driven text-to-table problem. We construct Q-STR from ball-by-ball match narratives using executable SQL templates and release two complementary splits: a 4,256-example coverage split for breadth and a 3,467-example controlled split spanning 348 reasoning templates for within-template diagnosis. Factorized metrics distinguish recovery of the answer-table structure from fidelity of its cell values. Across four language models and seven prompting strategies, models often recover plausible table structure while failing at grounded aggregation. Gemini-2.5-Flash is strongest overall, but even its best configuration reaches only 28.56 exact table match. For open-weight models, allocating output tokens to row-local evidence and computation improves cell fidelity more reliably than multi-call planning or self-consistency. Controlled comparisons further show that event identification and numeric fidelity are only partially coupled: execution pressure is the most consistent difficulty driver, while increasing output pressure shifts errors toward undercounting. Q-STR is deliberately a cricket diagnostic rather than a general benchmark of all narrative reasoning. Its single-domain scope, model-assisted construction, and absence of an executable code-generation baseline limit broader conclusions, but its controlled design exposes where structured reasoning from long narratives breaks down."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="upadhyay-etal-2026-q">
<titleInfo>
<title>Q-STR: Diagnosing Query-Driven Text-to-Table Reasoning in Cricket Narratives</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritam</namePart>
<namePart type="family">Upadhyay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naman</namePart>
<namePart type="family">Ahuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Baral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The Proceedings of Workshop on Document Intelligence and Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santosh</namePart>
<namePart type="family">T.Y.S.S.</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yova</namePart>
<namePart type="family">Kementchedjhieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aparna</namePart>
<namePart type="family">Garimella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufang</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-477-4</identifier>
</relatedItem>
<abstract>Many analytical questions over long narratives are structured even when their source documents are not. Answering them requires identifying relevant events, inducing a query-specific schema, grounding records in dispersed evidence, and computing the values of an answer table. We introduce Q-STR, a cricket-domain benchmark and diagnostic for this query-driven text-to-table problem. We construct Q-STR from ball-by-ball match narratives using executable SQL templates and release two complementary splits: a 4,256-example coverage split for breadth and a 3,467-example controlled split spanning 348 reasoning templates for within-template diagnosis. Factorized metrics distinguish recovery of the answer-table structure from fidelity of its cell values. Across four language models and seven prompting strategies, models often recover plausible table structure while failing at grounded aggregation. Gemini-2.5-Flash is strongest overall, but even its best configuration reaches only 28.56 exact table match. For open-weight models, allocating output tokens to row-local evidence and computation improves cell fidelity more reliably than multi-call planning or self-consistency. Controlled comparisons further show that event identification and numeric fidelity are only partially coupled: execution pressure is the most consistent difficulty driver, while increasing output pressure shifts errors toward undercounting. Q-STR is deliberately a cricket diagnostic rather than a general benchmark of all narrative reasoning. Its single-domain scope, model-assisted construction, and absence of an executable code-generation baseline limit broader conclusions, but its controlled design exposes where structured reasoning from long narratives breaks down.</abstract>
<identifier type="citekey">upadhyay-etal-2026-q</identifier>
<location>
<url>https://aclanthology.org/2026.docinsights-1.15/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>196</start>
<end>216</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Q-STR: Diagnosing Query-Driven Text-to-Table Reasoning in Cricket Narratives
%A Upadhyay, Ritam
%A Ahuja, Naman
%A Baral, Rishabh
%A Garimella, Aparna
%A Gupta, Vivek
%Y T.Y.S.S., Santosh
%Y Agarwal, Amit
%Y Gupta, Vivek
%Y Kementchedjhieva, Yova
%Y Garimella, Aparna
%Y Hou, Yufang
%S The Proceedings of Workshop on Document Intelligence and Understanding
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-477-4
%F upadhyay-etal-2026-q
%X Many analytical questions over long narratives are structured even when their source documents are not. Answering them requires identifying relevant events, inducing a query-specific schema, grounding records in dispersed evidence, and computing the values of an answer table. We introduce Q-STR, a cricket-domain benchmark and diagnostic for this query-driven text-to-table problem. We construct Q-STR from ball-by-ball match narratives using executable SQL templates and release two complementary splits: a 4,256-example coverage split for breadth and a 3,467-example controlled split spanning 348 reasoning templates for within-template diagnosis. Factorized metrics distinguish recovery of the answer-table structure from fidelity of its cell values. Across four language models and seven prompting strategies, models often recover plausible table structure while failing at grounded aggregation. Gemini-2.5-Flash is strongest overall, but even its best configuration reaches only 28.56 exact table match. For open-weight models, allocating output tokens to row-local evidence and computation improves cell fidelity more reliably than multi-call planning or self-consistency. Controlled comparisons further show that event identification and numeric fidelity are only partially coupled: execution pressure is the most consistent difficulty driver, while increasing output pressure shifts errors toward undercounting. Q-STR is deliberately a cricket diagnostic rather than a general benchmark of all narrative reasoning. Its single-domain scope, model-assisted construction, and absence of an executable code-generation baseline limit broader conclusions, but its controlled design exposes where structured reasoning from long narratives breaks down.
%U https://aclanthology.org/2026.docinsights-1.15/
%P 196-216
Markdown (Informal)
[Q-STR: Diagnosing Query-Driven Text-to-Table Reasoning in Cricket Narratives](https://aclanthology.org/2026.docinsights-1.15/) (Upadhyay et al., DocInsights 2026)
ACL