@inproceedings{jia-etal-2026-scout,
title = "{SCOUT}: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification",
author = "Jia, Junhao and
Zheng, Hanwen and
Wu, Yueyi and
Chen, Huangwei and
Wang, Haishuai and
Bu, Jiajun and
Wu, Lei",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.290/",
pages = "6413--6431",
ISBN = "979-8-89176-390-6",
abstract = "Natural language data is inherently noisy, yet standard interpretable models often rely on scalar similarities that obscure the true evidentiary basis of a prediction. This limitation is particularly detrimental to prototype-based classification, where traditional full-alignment mechanisms force non-informative background segments to match informative prototypes, yielding unstable or misleading explanations. To mitigate this, we present SCOUT, a novel paradigm that grounds prototype reasoning in the selective correspondence of discriminative fragments. Concretely, we represent each document as a discrete distribution over span embeddings and employ differentiable Unbalanced Optimal Transport (UOT) to align them with class-specific prototypes. Unlike standard methods, this mechanism enables the model to focus strictly on decisive evidence while leaving irrelevant noise unmatched via geometric mass suppression. To ensure verifiability, we anchor prototype supports to readable training spans, establishing a transparent bridge between input segments and stored knowledge. Comprehensive experiments on seven benchmarks demonstrate that SCOUT yields prototypes focused on semantically significant spans, significantly outperforming traditional rationale extraction and post-hoc attribution methods in terms of faithfulness and stability."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jia-etal-2026-scout">
<titleInfo>
<title>SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junhao</namePart>
<namePart type="family">Jia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanwen</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueyi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huangwei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haishuai</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Bu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Wu</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Natural language data is inherently noisy, yet standard interpretable models often rely on scalar similarities that obscure the true evidentiary basis of a prediction. This limitation is particularly detrimental to prototype-based classification, where traditional full-alignment mechanisms force non-informative background segments to match informative prototypes, yielding unstable or misleading explanations. To mitigate this, we present SCOUT, a novel paradigm that grounds prototype reasoning in the selective correspondence of discriminative fragments. Concretely, we represent each document as a discrete distribution over span embeddings and employ differentiable Unbalanced Optimal Transport (UOT) to align them with class-specific prototypes. Unlike standard methods, this mechanism enables the model to focus strictly on decisive evidence while leaving irrelevant noise unmatched via geometric mass suppression. To ensure verifiability, we anchor prototype supports to readable training spans, establishing a transparent bridge between input segments and stored knowledge. Comprehensive experiments on seven benchmarks demonstrate that SCOUT yields prototypes focused on semantically significant spans, significantly outperforming traditional rationale extraction and post-hoc attribution methods in terms of faithfulness and stability.</abstract>
<identifier type="citekey">jia-etal-2026-scout</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.290/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>6413</start>
<end>6431</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification
%A Jia, Junhao
%A Zheng, Hanwen
%A Wu, Yueyi
%A Chen, Huangwei
%A Wang, Haishuai
%A Bu, Jiajun
%A Wu, Lei
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F jia-etal-2026-scout
%X Natural language data is inherently noisy, yet standard interpretable models often rely on scalar similarities that obscure the true evidentiary basis of a prediction. This limitation is particularly detrimental to prototype-based classification, where traditional full-alignment mechanisms force non-informative background segments to match informative prototypes, yielding unstable or misleading explanations. To mitigate this, we present SCOUT, a novel paradigm that grounds prototype reasoning in the selective correspondence of discriminative fragments. Concretely, we represent each document as a discrete distribution over span embeddings and employ differentiable Unbalanced Optimal Transport (UOT) to align them with class-specific prototypes. Unlike standard methods, this mechanism enables the model to focus strictly on decisive evidence while leaving irrelevant noise unmatched via geometric mass suppression. To ensure verifiability, we anchor prototype supports to readable training spans, establishing a transparent bridge between input segments and stored knowledge. Comprehensive experiments on seven benchmarks demonstrate that SCOUT yields prototypes focused on semantically significant spans, significantly outperforming traditional rationale extraction and post-hoc attribution methods in terms of faithfulness and stability.
%U https://aclanthology.org/2026.acl-long.290/
%P 6413-6431
Markdown (Informal)
[SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification](https://aclanthology.org/2026.acl-long.290/) (Jia et al., ACL 2026)
ACL
- Junhao Jia, Hanwen Zheng, Yueyi Wu, Huangwei Chen, Haishuai Wang, Jiajun Bu, and Lei Wu. 2026. SCOUT: Selective Coupling via Optimal Unbalanced Transport for Interpretable Text Classification. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6413–6431, San Diego, California, United States. Association for Computational Linguistics.