@inproceedings{sheikh-2026-elision,
title = "Elision Markers in Mathematical Prose: Language Models Respond to Claimed Effort Rather Than Hidden Derivation Depth",
author = "Sheikh, Md. Faisal",
editor = "Valentino, Marco and
Ferreira, Deborah and
Thayaparan, Mokanarangan and
Ranaldi, Leonardo and
Cheng, Jo-Ku and
Freitas, Andre",
booktitle = "The Proceedings of the 4th Workshop on Mathematical Natural Language Processing ({M}ath{NLP} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mathnlp-main.5/",
pages = "57--68",
ISBN = "979-8-89176-468-2",
abstract = "Mathematical prose omits most of its own derivation and says so in passing. ``Clearly'', ``it follows that'' and ``a routine but tedious calculation yields'' mark places where an author has skipped work and left the reader to supply or trust it. Whether a model reading such a passage responds to the amount of mathematics that was skipped, or to the phrase announcing the skip, cannot be settled observationally, because in real proofs a marker claiming the gap is small usually introduces a gap that is small. We separate the two by generation. ELIDE-BENCH contains 4,800 machine-verified passages in which a claim sits behind an elision of known depth $d$ announced by a marker of known claimed effort $S$, with premise, visible steps and conclusion held byte-identical across the $S$ conditions. Evaluating five open-weight models, we find that $d$ has almost no influence on whether a false claim is accepted, while $S$ has a large one, and that the direction is the reverse of what a laziness account predicts. Swapping ``Clearly'' for ``a somewhat lengthy computation shows'', and changing nothing else, raises false acceptance by 11.6 and 12.5 points in two model families ($p < 10^{-29}$, paired within family). One tier of claimed effort moves a verdict as much as removing 2.3 to 2.6 hidden steps would. The models defer to asserted labour rather than to the mathematics that labour conceals, and one of them estimates elision depth accurately while still declining to use it."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheikh-2026-elision">
<titleInfo>
<title>Elision Markers in Mathematical Prose: Language Models Respond to Claimed Effort Rather Than Hidden Derivation Depth</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md.</namePart>
<namePart type="given">Faisal</namePart>
<namePart type="family">Sheikh</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 4th Workshop on Mathematical Natural Language Processing (MathNLP 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deborah</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mokanarangan</namePart>
<namePart type="family">Thayaparan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jo-Ku</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Freitas</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">979-8-89176-468-2</identifier>
</relatedItem>
<abstract>Mathematical prose omits most of its own derivation and says so in passing. “Clearly”, “it follows that” and “a routine but tedious calculation yields” mark places where an author has skipped work and left the reader to supply or trust it. Whether a model reading such a passage responds to the amount of mathematics that was skipped, or to the phrase announcing the skip, cannot be settled observationally, because in real proofs a marker claiming the gap is small usually introduces a gap that is small. We separate the two by generation. ELIDE-BENCH contains 4,800 machine-verified passages in which a claim sits behind an elision of known depth d announced by a marker of known claimed effort S, with premise, visible steps and conclusion held byte-identical across the S conditions. Evaluating five open-weight models, we find that d has almost no influence on whether a false claim is accepted, while S has a large one, and that the direction is the reverse of what a laziness account predicts. Swapping “Clearly” for “a somewhat lengthy computation shows”, and changing nothing else, raises false acceptance by 11.6 and 12.5 points in two model families (p < 10⁻29, paired within family). One tier of claimed effort moves a verdict as much as removing 2.3 to 2.6 hidden steps would. The models defer to asserted labour rather than to the mathematics that labour conceals, and one of them estimates elision depth accurately while still declining to use it.</abstract>
<identifier type="citekey">sheikh-2026-elision</identifier>
<location>
<url>https://aclanthology.org/2026.mathnlp-main.5/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>57</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Elision Markers in Mathematical Prose: Language Models Respond to Claimed Effort Rather Than Hidden Derivation Depth
%A Sheikh, Md. Faisal
%Y Valentino, Marco
%Y Ferreira, Deborah
%Y Thayaparan, Mokanarangan
%Y Ranaldi, Leonardo
%Y Cheng, Jo-Ku
%Y Freitas, Andre
%S The Proceedings of the 4th Workshop on Mathematical Natural Language Processing (MathNLP 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-468-2
%F sheikh-2026-elision
%X Mathematical prose omits most of its own derivation and says so in passing. “Clearly”, “it follows that” and “a routine but tedious calculation yields” mark places where an author has skipped work and left the reader to supply or trust it. Whether a model reading such a passage responds to the amount of mathematics that was skipped, or to the phrase announcing the skip, cannot be settled observationally, because in real proofs a marker claiming the gap is small usually introduces a gap that is small. We separate the two by generation. ELIDE-BENCH contains 4,800 machine-verified passages in which a claim sits behind an elision of known depth d announced by a marker of known claimed effort S, with premise, visible steps and conclusion held byte-identical across the S conditions. Evaluating five open-weight models, we find that d has almost no influence on whether a false claim is accepted, while S has a large one, and that the direction is the reverse of what a laziness account predicts. Swapping “Clearly” for “a somewhat lengthy computation shows”, and changing nothing else, raises false acceptance by 11.6 and 12.5 points in two model families (p < 10⁻29, paired within family). One tier of claimed effort moves a verdict as much as removing 2.3 to 2.6 hidden steps would. The models defer to asserted labour rather than to the mathematics that labour conceals, and one of them estimates elision depth accurately while still declining to use it.
%U https://aclanthology.org/2026.mathnlp-main.5/
%P 57-68
Markdown (Informal)
[Elision Markers in Mathematical Prose: Language Models Respond to Claimed Effort Rather Than Hidden Derivation Depth](https://aclanthology.org/2026.mathnlp-main.5/) (Sheikh, MathNLP 2026)
ACL