@inproceedings{chaudhary-nwogu-2026-explaining,
title = "Explaining the Influence of Nonverbal Streams Across Sentence Types",
author = "Chaudhary, Lipisha and
Nwogu, Ifeoma",
editor = "Arad, Dana and
Belinkov, Yonatan and
Chen, Hanjie and
Feldhus, Nils and
Mueller, Aaron and
Mohebbi, Hosein and
Sarti, Gabriele and
Tutek, Martin",
booktitle = "Proceedings of the 9th {B}lackbox{NLP} Workshop: Analyzing and Interpreting Neural Networks for {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.blackboxnlp-1.52/",
pages = "919--936",
ISBN = "979-8-89176-476-7",
abstract = "Sign Language Translation (SLT) models integrate multiple visual channels, including the hands, body, and face, to generate written text, yet it remains unclear which channels the model actually relies on. We introduce Causal Stream Intervention (CSI), an intervention-based framework that measures each channel{'}s contribution by suppressing it during decoding and observing the change in the model{'}s predictions. This goes beyond attention weights, which show where a model looks but not what it depends on. Across two American Sign Language (ASL) datasets, we find that hand streams drive content-word prediction, while face and body streams contribute in a more variable, context-dependent way, with no single stream consistently dominating during question generation. Attention and routing scores offer a partial signal, but targeted interventions, particularly in later decoding layers, reveal functional stream use more faithfully."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaudhary-nwogu-2026-explaining">
<titleInfo>
<title>Explaining the Influence of Nonverbal Streams Across Sentence Types</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lipisha</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ifeoma</namePart>
<namePart type="family">Nwogu</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 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Arad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanjie</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Mueller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hosein</namePart>
<namePart type="family">Mohebbi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Sarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Tutek</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">979-8-89176-476-7</identifier>
</relatedItem>
<abstract>Sign Language Translation (SLT) models integrate multiple visual channels, including the hands, body, and face, to generate written text, yet it remains unclear which channels the model actually relies on. We introduce Causal Stream Intervention (CSI), an intervention-based framework that measures each channel’s contribution by suppressing it during decoding and observing the change in the model’s predictions. This goes beyond attention weights, which show where a model looks but not what it depends on. Across two American Sign Language (ASL) datasets, we find that hand streams drive content-word prediction, while face and body streams contribute in a more variable, context-dependent way, with no single stream consistently dominating during question generation. Attention and routing scores offer a partial signal, but targeted interventions, particularly in later decoding layers, reveal functional stream use more faithfully.</abstract>
<identifier type="citekey">chaudhary-nwogu-2026-explaining</identifier>
<location>
<url>https://aclanthology.org/2026.blackboxnlp-1.52/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>919</start>
<end>936</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Explaining the Influence of Nonverbal Streams Across Sentence Types
%A Chaudhary, Lipisha
%A Nwogu, Ifeoma
%Y Arad, Dana
%Y Belinkov, Yonatan
%Y Chen, Hanjie
%Y Feldhus, Nils
%Y Mueller, Aaron
%Y Mohebbi, Hosein
%Y Sarti, Gabriele
%Y Tutek, Martin
%S Proceedings of the 9th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-476-7
%F chaudhary-nwogu-2026-explaining
%X Sign Language Translation (SLT) models integrate multiple visual channels, including the hands, body, and face, to generate written text, yet it remains unclear which channels the model actually relies on. We introduce Causal Stream Intervention (CSI), an intervention-based framework that measures each channel’s contribution by suppressing it during decoding and observing the change in the model’s predictions. This goes beyond attention weights, which show where a model looks but not what it depends on. Across two American Sign Language (ASL) datasets, we find that hand streams drive content-word prediction, while face and body streams contribute in a more variable, context-dependent way, with no single stream consistently dominating during question generation. Attention and routing scores offer a partial signal, but targeted interventions, particularly in later decoding layers, reveal functional stream use more faithfully.
%U https://aclanthology.org/2026.blackboxnlp-1.52/
%P 919-936
Markdown (Informal)
[Explaining the Influence of Nonverbal Streams Across Sentence Types](https://aclanthology.org/2026.blackboxnlp-1.52/) (Chaudhary & Nwogu, BlackboxNLP 2026)
ACL