@inproceedings{morita-2026-daikoku,
title = "Daikoku at the {F}in{E}val 2026: Multi-Stage Labelling with Forced-Choice Adjudication",
author = "Morita, Kyosuke",
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-1.70/",
pages = "783--792",
ISBN = "979-8-89176-466-8",
abstract = "This paper describes our submission to SubTask 2 of the FinEval 2026 Multilingual Financial Language Understanding Challenge, Japanese Financial Implicit Communication Recognition (JF-ICR), which places a company{'}s question-answer on a five-point commitment scale. Our submitted system, a three-stage pipeline, scores 15/15 public and 33/35 private, 4th of 10. A single open-weight model labels each of the 50 test items independently by verbaliser scoring; that labelling is audited against the class distribution the organisers publish in advance, which yields a label-free lower bound $F$ on its error count and names the classes those errors sit in; each over-full class is then handed back to the model as a forced choice over its own members, with the exact number of mislabelled items asserted. The audit opens at $F{=}3$ and closes at $F{=}0$. Enforcing the same counts directly, by min-cost assignment, also reaches $F{=}0$ but recovers only the errors already nearest the decision boundary. The official score bounds what a floor of zero is worth: two of the 50 items are wrong beneath it, and, both the submitted labelling and the gold being balanced, those two errors can only form a compensating transposition."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morita-2026-daikoku">
<titleInfo>
<title>Daikoku at the FinEval 2026: Multi-Stage Labelling with Forced-Choice Adjudication</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kyosuke</namePart>
<namePart type="family">Morita</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>This paper describes our submission to SubTask 2 of the FinEval 2026 Multilingual Financial Language Understanding Challenge, Japanese Financial Implicit Communication Recognition (JF-ICR), which places a company’s question-answer on a five-point commitment scale. Our submitted system, a three-stage pipeline, scores 15/15 public and 33/35 private, 4th of 10. A single open-weight model labels each of the 50 test items independently by verbaliser scoring; that labelling is audited against the class distribution the organisers publish in advance, which yields a label-free lower bound F on its error count and names the classes those errors sit in; each over-full class is then handed back to the model as a forced choice over its own members, with the exact number of mislabelled items asserted. The audit opens at F=3 and closes at F=0. Enforcing the same counts directly, by min-cost assignment, also reaches F=0 but recovers only the errors already nearest the decision boundary. The official score bounds what a floor of zero is worth: two of the 50 items are wrong beneath it, and, both the submitted labelling and the gold being balanced, those two errors can only form a compensating transposition.</abstract>
<identifier type="citekey">morita-2026-daikoku</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.70/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>783</start>
<end>792</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Daikoku at the FinEval 2026: Multi-Stage Labelling with Forced-Choice Adjudication
%A Morita, Kyosuke
%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 morita-2026-daikoku
%X This paper describes our submission to SubTask 2 of the FinEval 2026 Multilingual Financial Language Understanding Challenge, Japanese Financial Implicit Communication Recognition (JF-ICR), which places a company’s question-answer on a five-point commitment scale. Our submitted system, a three-stage pipeline, scores 15/15 public and 33/35 private, 4th of 10. A single open-weight model labels each of the 50 test items independently by verbaliser scoring; that labelling is audited against the class distribution the organisers publish in advance, which yields a label-free lower bound F on its error count and names the classes those errors sit in; each over-full class is then handed back to the model as a forced choice over its own members, with the exact number of mislabelled items asserted. The audit opens at F=3 and closes at F=0. Enforcing the same counts directly, by min-cost assignment, also reaches F=0 but recovers only the errors already nearest the decision boundary. The official score bounds what a floor of zero is worth: two of the 50 items are wrong beneath it, and, both the submitted labelling and the gold being balanced, those two errors can only form a compensating transposition.
%U https://aclanthology.org/2026.finnlp-1.70/
%P 783-792
Markdown (Informal)
[Daikoku at the FinEval 2026: Multi-Stage Labelling with Forced-Choice Adjudication](https://aclanthology.org/2026.finnlp-1.70/) (Morita, FinNLP 2026)
ACL