@inproceedings{xu-cao-2026-token,
title = "Token Crit at the {F}in{E}val 2026: Role-Specialized, Validation-Gated {LLM} Workflows for {JF}-{ICR} and Multilingual Financial {Q}{\&}{A}",
author = "Xu, Anke and
Cao, Wenbo",
editor = "Huang, Jimin and
Lee, Yongjae and
Ananiadou, Sophia and
Chen, Hsin-Hsi and
Takamura, Hiroya and
Chen, Chung-Chi",
booktitle = "Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.finnlp-1.74/",
pages = "822--828",
ISBN = "979-8-89176-466-8",
abstract = "Multi-stage LLM workflows can degrade correct outputs when intermediate analyses revise shared state without constraint. We present validation-gated systems for two FinEval 2026 tasks: Japanese Financial Implicit Communication Recognition (JF-ICR) and multilingual financial Q{\&}A (PolyFiQA). Specialized roles produce structured proposals, while task-specific validators admit only scoped label transitions for JF-ICR or source-linked evidence for PolyFiQA. On the 253-example JF-ICR public development set, the final workflow reaches 62.1{\%} accuracy, compared with 51.0{\%} for the stronger direct LLM baseline and 54.9{\%} for a majority-class baseline. Applying all final-stage proposals would yield a net loss of two correct predictions, whereas gated admission yields a net gain of 11. On 76 PolyFiQA training examples, the final workflow yields a modest overall ROUGE-1 improvement (0.3399 to 0.3425) but raises evidence-section ROUGE-1 F1 from 0.1570 to 0.5132. Together, these results suggest that validation-gated updating is most effective for narrow, checkable changes; open-ended synthesis still requires recall-aware admission and closer alignment between validation and answer generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-cao-2026-token">
<titleInfo>
<title>Token Crit at the FinEval 2026: Role-Specialized, Validation-Gated LLM Workflows for JF-ICR and Multilingual Financial Q&A</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anke</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbo</namePart>
<namePart type="family">Cao</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 11th Workshop on Financial Technology and Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jimin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongjae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroya</namePart>
<namePart type="family">Takamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Chi</namePart>
<namePart type="family">Chen</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">979-8-89176-466-8</identifier>
</relatedItem>
<abstract>Multi-stage LLM workflows can degrade correct outputs when intermediate analyses revise shared state without constraint. We present validation-gated systems for two FinEval 2026 tasks: Japanese Financial Implicit Communication Recognition (JF-ICR) and multilingual financial Q&A (PolyFiQA). Specialized roles produce structured proposals, while task-specific validators admit only scoped label transitions for JF-ICR or source-linked evidence for PolyFiQA. On the 253-example JF-ICR public development set, the final workflow reaches 62.1% accuracy, compared with 51.0% for the stronger direct LLM baseline and 54.9% for a majority-class baseline. Applying all final-stage proposals would yield a net loss of two correct predictions, whereas gated admission yields a net gain of 11. On 76 PolyFiQA training examples, the final workflow yields a modest overall ROUGE-1 improvement (0.3399 to 0.3425) but raises evidence-section ROUGE-1 F1 from 0.1570 to 0.5132. Together, these results suggest that validation-gated updating is most effective for narrow, checkable changes; open-ended synthesis still requires recall-aware admission and closer alignment between validation and answer generation.</abstract>
<identifier type="citekey">xu-cao-2026-token</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.74/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>822</start>
<end>828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Token Crit at the FinEval 2026: Role-Specialized, Validation-Gated LLM Workflows for JF-ICR and Multilingual Financial Q&A
%A Xu, Anke
%A Cao, Wenbo
%Y Huang, Jimin
%Y Lee, Yongjae
%Y Ananiadou, Sophia
%Y Chen, Hsin-Hsi
%Y Takamura, Hiroya
%Y Chen, Chung-Chi
%S Proceedings of the 11th Workshop on Financial Technology and Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-466-8
%F xu-cao-2026-token
%X Multi-stage LLM workflows can degrade correct outputs when intermediate analyses revise shared state without constraint. We present validation-gated systems for two FinEval 2026 tasks: Japanese Financial Implicit Communication Recognition (JF-ICR) and multilingual financial Q&A (PolyFiQA). Specialized roles produce structured proposals, while task-specific validators admit only scoped label transitions for JF-ICR or source-linked evidence for PolyFiQA. On the 253-example JF-ICR public development set, the final workflow reaches 62.1% accuracy, compared with 51.0% for the stronger direct LLM baseline and 54.9% for a majority-class baseline. Applying all final-stage proposals would yield a net loss of two correct predictions, whereas gated admission yields a net gain of 11. On 76 PolyFiQA training examples, the final workflow yields a modest overall ROUGE-1 improvement (0.3399 to 0.3425) but raises evidence-section ROUGE-1 F1 from 0.1570 to 0.5132. Together, these results suggest that validation-gated updating is most effective for narrow, checkable changes; open-ended synthesis still requires recall-aware admission and closer alignment between validation and answer generation.
%U https://aclanthology.org/2026.finnlp-1.74/
%P 822-828
Markdown (Informal)
[Token Crit at the FinEval 2026: Role-Specialized, Validation-Gated LLM Workflows for JF-ICR and Multilingual Financial Q&A](https://aclanthology.org/2026.finnlp-1.74/) (Xu & Cao, FinNLP 2026)
ACL