@inproceedings{ahmed-etal-2026-finstruct,
title = "{FINSTRUCT}: {LLM}-Based Logical Structure Recovery for Financial Filings",
author = "Ahmed, Mazen Mohmed Nasr Mohamed and
Long, Yunfei and
Kampouridis, Michael and
Tattersall, Rachel and
Clague, Kimberley",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.104/",
pages = "1804--1818",
ISBN = "979-8-89176-460-6",
abstract = "Financial-filings workflows depend on more than extracting reported values: each number must be placed in the document context that makes it reviewable, comparable, and auditable. In practice, this logical structure{---}including the relevant section, note, heading, row, column, period, currency, and surrounding text{---}is often clear to professional reviewers but only partially encoded in inline XBRL markup. As a result, rule-based parsers can work on familiar layouts yet fail silently when document structure departs from expected templates. We present FINSTRUCT, an on-premise LLM system designed for confidential financial-document workflows. FINSTRUCT runs locally on a single 16 GB GPU, requires no task-specific fine-tuning, predicts nine structural fields for each reported fact, and provides reviewer-facing rationales together with repeated-sample agreement signals for human-in-the-loop review. On 1,493 manually annotated facts from five UK FRS 102 filings produced by a single accounts-production stack, FINSTRUCT raises macro accuracy from 50.6{\%} to 74.8{\%} and micro accuracy from 63.1{\%} to 85.1{\%} over a deterministic parser. More importantly for deployment, it recovers structure at 83.5{\%} accuracy on a filing where the rule-based parser silently misses whole sections, and its agreement signal separates more reliable predictions from cases requiring review. These results position logical structure recovery as a practical document-understanding layer for regulated financial automation, rather than a conventional parsing problem alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahmed-etal-2026-finstruct">
<titleInfo>
<title>FINSTRUCT: LLM-Based Logical Structure Recovery for Financial Filings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mazen</namePart>
<namePart type="given">Mohmed</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="given">Mohamed</namePart>
<namePart type="family">Ahmed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunfei</namePart>
<namePart type="family">Long</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Kampouridis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Tattersall</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kimberley</namePart>
<namePart type="family">Clague</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</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">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Financial-filings workflows depend on more than extracting reported values: each number must be placed in the document context that makes it reviewable, comparable, and auditable. In practice, this logical structure—including the relevant section, note, heading, row, column, period, currency, and surrounding text—is often clear to professional reviewers but only partially encoded in inline XBRL markup. As a result, rule-based parsers can work on familiar layouts yet fail silently when document structure departs from expected templates. We present FINSTRUCT, an on-premise LLM system designed for confidential financial-document workflows. FINSTRUCT runs locally on a single 16 GB GPU, requires no task-specific fine-tuning, predicts nine structural fields for each reported fact, and provides reviewer-facing rationales together with repeated-sample agreement signals for human-in-the-loop review. On 1,493 manually annotated facts from five UK FRS 102 filings produced by a single accounts-production stack, FINSTRUCT raises macro accuracy from 50.6% to 74.8% and micro accuracy from 63.1% to 85.1% over a deterministic parser. More importantly for deployment, it recovers structure at 83.5% accuracy on a filing where the rule-based parser silently misses whole sections, and its agreement signal separates more reliable predictions from cases requiring review. These results position logical structure recovery as a practical document-understanding layer for regulated financial automation, rather than a conventional parsing problem alone.</abstract>
<identifier type="citekey">ahmed-etal-2026-finstruct</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.104/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1804</start>
<end>1818</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FINSTRUCT: LLM-Based Logical Structure Recovery for Financial Filings
%A Ahmed, Mazen Mohmed Nasr Mohamed
%A Long, Yunfei
%A Kampouridis, Michael
%A Tattersall, Rachel
%A Clague, Kimberley
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F ahmed-etal-2026-finstruct
%X Financial-filings workflows depend on more than extracting reported values: each number must be placed in the document context that makes it reviewable, comparable, and auditable. In practice, this logical structure—including the relevant section, note, heading, row, column, period, currency, and surrounding text—is often clear to professional reviewers but only partially encoded in inline XBRL markup. As a result, rule-based parsers can work on familiar layouts yet fail silently when document structure departs from expected templates. We present FINSTRUCT, an on-premise LLM system designed for confidential financial-document workflows. FINSTRUCT runs locally on a single 16 GB GPU, requires no task-specific fine-tuning, predicts nine structural fields for each reported fact, and provides reviewer-facing rationales together with repeated-sample agreement signals for human-in-the-loop review. On 1,493 manually annotated facts from five UK FRS 102 filings produced by a single accounts-production stack, FINSTRUCT raises macro accuracy from 50.6% to 74.8% and micro accuracy from 63.1% to 85.1% over a deterministic parser. More importantly for deployment, it recovers structure at 83.5% accuracy on a filing where the rule-based parser silently misses whole sections, and its agreement signal separates more reliable predictions from cases requiring review. These results position logical structure recovery as a practical document-understanding layer for regulated financial automation, rather than a conventional parsing problem alone.
%U https://aclanthology.org/2026.emnlp-industry.104/
%P 1804-1818
Markdown (Informal)
[FINSTRUCT: LLM-Based Logical Structure Recovery for Financial Filings](https://aclanthology.org/2026.emnlp-industry.104/) (Ahmed et al., EMNLP 2026)
ACL
- Mazen Mohmed Nasr Mohamed Ahmed, Yunfei Long, Michael Kampouridis, Rachel Tattersall, and Kimberley Clague. 2026. FINSTRUCT: LLM-Based Logical Structure Recovery for Financial Filings. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 1804–1818, Budapest, Hungary. Association for Computational Linguistics.