@inproceedings{mehrotra-etal-2026-ten,
title = "{TEN}: Table Explicitization, Neurosymbolically",
author = "Mehrotra, Nikita and
Kumar, Aayush and
Gulwani, Sumit and
Radhakrishna, Arjun and
Tiwari, Ashish",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.138/",
pages = "2050--2086",
ISBN = "979-8-89176-394-4",
abstract = "We present TEN, a neurosymbolic approach for extracting tabular data from semistructured text such as copy-pasted content from PDFs, emails, or OCR-flattened outputs. This task poses real-world challenges in domains like finance and healthcare, where manual copy-paste into spreadsheets introduces errors and OCR distortions compromise data integrity, leading to financial losses and flawed decisions.Purely neural methods suffer from hallucinations and structural inconsistencies, hindering deployment robustness. TEN addresses this via a novel triadic feedback loop that iteratively refines table hypotheses to enforce constraints and achieve verifiable convergence.Experiments show TEN outperforms neural baselines in exact match accuracy and lower hallucination rates. A 21-participant user study rates TEN tables more accurate and preferred in over 60{\%} of pairwise comparisons, though verification and correction effort did not differ significantly between conditions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehrotra-etal-2026-ten">
<titleInfo>
<title>TEN: Table Explicitization, Neurosymbolically</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikita</namePart>
<namePart type="family">Mehrotra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aayush</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumit</namePart>
<namePart type="family">Gulwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arjun</namePart>
<namePart type="family">Radhakrishna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Tiwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>We present TEN, a neurosymbolic approach for extracting tabular data from semistructured text such as copy-pasted content from PDFs, emails, or OCR-flattened outputs. This task poses real-world challenges in domains like finance and healthcare, where manual copy-paste into spreadsheets introduces errors and OCR distortions compromise data integrity, leading to financial losses and flawed decisions.Purely neural methods suffer from hallucinations and structural inconsistencies, hindering deployment robustness. TEN addresses this via a novel triadic feedback loop that iteratively refines table hypotheses to enforce constraints and achieve verifiable convergence.Experiments show TEN outperforms neural baselines in exact match accuracy and lower hallucination rates. A 21-participant user study rates TEN tables more accurate and preferred in over 60% of pairwise comparisons, though verification and correction effort did not differ significantly between conditions.</abstract>
<identifier type="citekey">mehrotra-etal-2026-ten</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.138/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2050</start>
<end>2086</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TEN: Table Explicitization, Neurosymbolically
%A Mehrotra, Nikita
%A Kumar, Aayush
%A Gulwani, Sumit
%A Radhakrishna, Arjun
%A Tiwari, Ashish
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F mehrotra-etal-2026-ten
%X We present TEN, a neurosymbolic approach for extracting tabular data from semistructured text such as copy-pasted content from PDFs, emails, or OCR-flattened outputs. This task poses real-world challenges in domains like finance and healthcare, where manual copy-paste into spreadsheets introduces errors and OCR distortions compromise data integrity, leading to financial losses and flawed decisions.Purely neural methods suffer from hallucinations and structural inconsistencies, hindering deployment robustness. TEN addresses this via a novel triadic feedback loop that iteratively refines table hypotheses to enforce constraints and achieve verifiable convergence.Experiments show TEN outperforms neural baselines in exact match accuracy and lower hallucination rates. A 21-participant user study rates TEN tables more accurate and preferred in over 60% of pairwise comparisons, though verification and correction effort did not differ significantly between conditions.
%U https://aclanthology.org/2026.acl-industry.138/
%P 2050-2086
Markdown (Informal)
[TEN: Table Explicitization, Neurosymbolically](https://aclanthology.org/2026.acl-industry.138/) (Mehrotra et al., ACL 2026)
ACL
- Nikita Mehrotra, Aayush Kumar, Sumit Gulwani, Arjun Radhakrishna, and Ashish Tiwari. 2026. TEN: Table Explicitization, Neurosymbolically. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 2050–2086, San Diego, California, USA. Association for Computational Linguistics.