@inproceedings{huang-etal-2026-nash,
title = "{NASH}: Numerically Aware Scoring Heuristic for Robust Semantic Similarity",
author = "Huang, Yu-Shiang and
Lee, Yun-Yu and
Chou, Tzu-Hsin and
Lin, Che and
Wang, Chuan-Ju",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1119/",
pages = "22303--22317",
ISBN = "979-8-89176-395-1",
abstract = "Numerical precision is critical in financial NLP, yet embedding-based semantic similarity metrics exhibit numerical blindness{---}failing to distinguish contradictory values within similar contexts. We introduce NASH (Numerically Aware Scoring Hueristic), a model-agnostic metric that decouples numerical verification from textual semantic evaluation through a three-stage pipeline: (1) modal separation via numeric masking, (2) dual-channel similarity estimation through masked-text similarity and context-aware numeric alignment, and (3) IDF-weighted aggregation. NASH functions as a drop-in enhancement to existing embedding-based metrics. Validated on our proposed NumFinE financial numerical evaluation benchmark and established semantic similarity datasets (STS-B, Financial-STS), NASH achieves substantial improvements in numerical sensitivity (up to +159.6{\%} on listwise ranking) while preserving general semantic performance, establishing a reliable standard for numeracy-aware evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2026-nash">
<titleInfo>
<title>NASH: Numerically Aware Scoring Heuristic for Robust Semantic Similarity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu-Shiang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Yu</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tzu-Hsin</namePart>
<namePart type="family">Chou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Che</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuan-Ju</namePart>
<namePart type="family">Wang</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Numerical precision is critical in financial NLP, yet embedding-based semantic similarity metrics exhibit numerical blindness—failing to distinguish contradictory values within similar contexts. We introduce NASH (Numerically Aware Scoring Hueristic), a model-agnostic metric that decouples numerical verification from textual semantic evaluation through a three-stage pipeline: (1) modal separation via numeric masking, (2) dual-channel similarity estimation through masked-text similarity and context-aware numeric alignment, and (3) IDF-weighted aggregation. NASH functions as a drop-in enhancement to existing embedding-based metrics. Validated on our proposed NumFinE financial numerical evaluation benchmark and established semantic similarity datasets (STS-B, Financial-STS), NASH achieves substantial improvements in numerical sensitivity (up to +159.6% on listwise ranking) while preserving general semantic performance, establishing a reliable standard for numeracy-aware evaluation.</abstract>
<identifier type="citekey">huang-etal-2026-nash</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1119/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>22303</start>
<end>22317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NASH: Numerically Aware Scoring Heuristic for Robust Semantic Similarity
%A Huang, Yu-Shiang
%A Lee, Yun-Yu
%A Chou, Tzu-Hsin
%A Lin, Che
%A Wang, Chuan-Ju
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F huang-etal-2026-nash
%X Numerical precision is critical in financial NLP, yet embedding-based semantic similarity metrics exhibit numerical blindness—failing to distinguish contradictory values within similar contexts. We introduce NASH (Numerically Aware Scoring Hueristic), a model-agnostic metric that decouples numerical verification from textual semantic evaluation through a three-stage pipeline: (1) modal separation via numeric masking, (2) dual-channel similarity estimation through masked-text similarity and context-aware numeric alignment, and (3) IDF-weighted aggregation. NASH functions as a drop-in enhancement to existing embedding-based metrics. Validated on our proposed NumFinE financial numerical evaluation benchmark and established semantic similarity datasets (STS-B, Financial-STS), NASH achieves substantial improvements in numerical sensitivity (up to +159.6% on listwise ranking) while preserving general semantic performance, establishing a reliable standard for numeracy-aware evaluation.
%U https://aclanthology.org/2026.findings-acl.1119/
%P 22303-22317
Markdown (Informal)
[NASH: Numerically Aware Scoring Heuristic for Robust Semantic Similarity](https://aclanthology.org/2026.findings-acl.1119/) (Huang et al., Findings 2026)
ACL