@inproceedings{chaz-rivera-etal-2026-idiomatic,
title = "Idiomatic Blind Spots in Discrete Diffusion Models",
author = "Chaz Rivera, Joshua and
Gripon, Vincent and
Pasdeloup, Bastien",
editor = {Aziz, Wilker and
Berant, Jonathan and
Eikema, Bryan and
Ilia, Evgenia and
de Marneffe, Marie-Catherine and
Plank, Barbara and
Shelmanov, Artem and
Swayamdipta, Swabha and
Tiedemann, J{\"o}rg and
Vazhentsev, Artem and
V{\'a}zquez, Ra{\'u}l and
Zerva, Chrysoula},
booktitle = "The Proceedings of the Third Workshop on Uncertainty-Aware {NLP}",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.uncertainlp-main.7/",
pages = "81--93",
ISBN = "979-8-89176-486-6",
abstract = "Discrete diffusion language models have emerged as a compelling alternative to autoregressive approaches, offering a range of structural advantages. This is due to their bidirectional attention allowing a global semantic view across intermediate denoising steps that enables flexible, order-agnostic generation. Despite this promise, they have received considerably less attention in ongoing research, and existing work has focused narrowly on mathematics and formal reasoning tasks. Their language comprehension capabilities, particularly for figurative language, remain entirely unevaluated, leaving open fundamental questions about how these models handle complex idiomatic structures, especially for languages other than English. We find that diffusion models do possess many strong idiomatic processing abilities, demonstrated through competitive token recovery in cloze tests and strong semantic ability from multiple-choice accuracy. However, this advantage fails to surface during inference as confidence-based demasking appears poorly suited for idioms, as early committed tokens override internal representations and discourage certain types of multi-token structures from generation, limiting their linguistic abilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaz-rivera-etal-2026-idiomatic">
<titleInfo>
<title>Idiomatic Blind Spots in Discrete Diffusion Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Chaz Rivera</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Gripon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bastien</namePart>
<namePart type="family">Pasdeloup</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>The Proceedings of the Third Workshop on Uncertainty-Aware NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wilker</namePart>
<namePart type="family">Aziz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Berant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Eikema</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgenia</namePart>
<namePart type="family">Ilia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Shelmanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Vazhentsev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chrysoula</namePart>
<namePart type="family">Zerva</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">979-8-89176-486-6</identifier>
</relatedItem>
<abstract>Discrete diffusion language models have emerged as a compelling alternative to autoregressive approaches, offering a range of structural advantages. This is due to their bidirectional attention allowing a global semantic view across intermediate denoising steps that enables flexible, order-agnostic generation. Despite this promise, they have received considerably less attention in ongoing research, and existing work has focused narrowly on mathematics and formal reasoning tasks. Their language comprehension capabilities, particularly for figurative language, remain entirely unevaluated, leaving open fundamental questions about how these models handle complex idiomatic structures, especially for languages other than English. We find that diffusion models do possess many strong idiomatic processing abilities, demonstrated through competitive token recovery in cloze tests and strong semantic ability from multiple-choice accuracy. However, this advantage fails to surface during inference as confidence-based demasking appears poorly suited for idioms, as early committed tokens override internal representations and discourage certain types of multi-token structures from generation, limiting their linguistic abilities.</abstract>
<identifier type="citekey">chaz-rivera-etal-2026-idiomatic</identifier>
<location>
<url>https://aclanthology.org/2026.uncertainlp-main.7/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>81</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Idiomatic Blind Spots in Discrete Diffusion Models
%A Chaz Rivera, Joshua
%A Gripon, Vincent
%A Pasdeloup, Bastien
%Y Aziz, Wilker
%Y Berant, Jonathan
%Y Eikema, Bryan
%Y Ilia, Evgenia
%Y de Marneffe, Marie-Catherine
%Y Plank, Barbara
%Y Shelmanov, Artem
%Y Swayamdipta, Swabha
%Y Tiedemann, Jörg
%Y Vazhentsev, Artem
%Y Vázquez, Raúl
%Y Zerva, Chrysoula
%S The Proceedings of the Third Workshop on Uncertainty-Aware NLP
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-486-6
%F chaz-rivera-etal-2026-idiomatic
%X Discrete diffusion language models have emerged as a compelling alternative to autoregressive approaches, offering a range of structural advantages. This is due to their bidirectional attention allowing a global semantic view across intermediate denoising steps that enables flexible, order-agnostic generation. Despite this promise, they have received considerably less attention in ongoing research, and existing work has focused narrowly on mathematics and formal reasoning tasks. Their language comprehension capabilities, particularly for figurative language, remain entirely unevaluated, leaving open fundamental questions about how these models handle complex idiomatic structures, especially for languages other than English. We find that diffusion models do possess many strong idiomatic processing abilities, demonstrated through competitive token recovery in cloze tests and strong semantic ability from multiple-choice accuracy. However, this advantage fails to surface during inference as confidence-based demasking appears poorly suited for idioms, as early committed tokens override internal representations and discourage certain types of multi-token structures from generation, limiting their linguistic abilities.
%U https://aclanthology.org/2026.uncertainlp-main.7/
%P 81-93
Markdown (Informal)
[Idiomatic Blind Spots in Discrete Diffusion Models](https://aclanthology.org/2026.uncertainlp-main.7/) (Chaz Rivera et al., UncertaiNLP 2026)
ACL
- Joshua Chaz Rivera, Vincent Gripon, and Bastien Pasdeloup. 2026. Idiomatic Blind Spots in Discrete Diffusion Models. In The Proceedings of the Third Workshop on Uncertainty-Aware NLP, pages 81–93, Budapest, Hungary. Association for Computational Linguistics.