@inproceedings{li-wang-2026-hx,
title = "{HX}-Fin at {F}in{E}val 2026: Precision-Anchored Answer Refinement and Multi-Model Evidence Selection for Multilingual Financial Question Answering",
author = "Li, Peng and
Wang, Yinchun",
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-1.76/",
pages = "835--840",
ISBN = "979-8-89176-466-8",
abstract = "Financial question answering requires both a concise answer grounded in news and a supporting excerpt from heterogeneous financial statements. We present a training-free modular pipeline that separates the two objectives, where the evidence module relies on the frozen output of the answer module. The Answer module constructs a high-precision core using Pairwise Selection, synthesizes a higher-recall extended answer from five candidate views, and selectively transfers supported content through Delta Augmentation and Claim Pruning. The Evidence module applies generate{--}refine{--}MBR selection to obtain a primary evidence candidate, independently generates an alternative with \textsc{Qwen3.6-Think}, and replaces the default only under a conservative decision policy. We evaluate answer module performance on 76 examples scored by a rubric-guided LLM judge. On the 0{--}4 judging scale, Pairwise Selection raises the average answer score from 2.316 to 2.540 ($+0.224$), while Delta Augmentation and Claim Pruning provide further gains of $+0.079$ and $+0.066$, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-wang-2026-hx">
<titleInfo>
<title>HX-Fin at FinEval 2026: Precision-Anchored Answer Refinement and Multi-Model Evidence Selection for Multilingual Financial Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinchun</namePart>
<namePart type="family">Wang</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>Financial question answering requires both a concise answer grounded in news and a supporting excerpt from heterogeneous financial statements. We present a training-free modular pipeline that separates the two objectives, where the evidence module relies on the frozen output of the answer module. The Answer module constructs a high-precision core using Pairwise Selection, synthesizes a higher-recall extended answer from five candidate views, and selectively transfers supported content through Delta Augmentation and Claim Pruning. The Evidence module applies generate–refine–MBR selection to obtain a primary evidence candidate, independently generates an alternative with Qwen3.6-Think, and replaces the default only under a conservative decision policy. We evaluate answer module performance on 76 examples scored by a rubric-guided LLM judge. On the 0–4 judging scale, Pairwise Selection raises the average answer score from 2.316 to 2.540 (+0.224), while Delta Augmentation and Claim Pruning provide further gains of +0.079 and +0.066, respectively.</abstract>
<identifier type="citekey">li-wang-2026-hx</identifier>
<location>
<url>https://aclanthology.org/2026.finnlp-1.76/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>835</start>
<end>840</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HX-Fin at FinEval 2026: Precision-Anchored Answer Refinement and Multi-Model Evidence Selection for Multilingual Financial Question Answering
%A Li, Peng
%A Wang, Yinchun
%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 li-wang-2026-hx
%X Financial question answering requires both a concise answer grounded in news and a supporting excerpt from heterogeneous financial statements. We present a training-free modular pipeline that separates the two objectives, where the evidence module relies on the frozen output of the answer module. The Answer module constructs a high-precision core using Pairwise Selection, synthesizes a higher-recall extended answer from five candidate views, and selectively transfers supported content through Delta Augmentation and Claim Pruning. The Evidence module applies generate–refine–MBR selection to obtain a primary evidence candidate, independently generates an alternative with Qwen3.6-Think, and replaces the default only under a conservative decision policy. We evaluate answer module performance on 76 examples scored by a rubric-guided LLM judge. On the 0–4 judging scale, Pairwise Selection raises the average answer score from 2.316 to 2.540 (+0.224), while Delta Augmentation and Claim Pruning provide further gains of +0.079 and +0.066, respectively.
%U https://aclanthology.org/2026.finnlp-1.76/
%P 835-840
Markdown (Informal)
[HX-Fin at FinEval 2026: Precision-Anchored Answer Refinement and Multi-Model Evidence Selection for Multilingual Financial Question Answering](https://aclanthology.org/2026.finnlp-1.76/) (Li & Wang, FinNLP 2026)
ACL