@inproceedings{faisal-chowdhury-2026-cuetluminaries,
title = "{CUETL}uminaries at {S}em{E}val-2026 Task 11 Disentangling Logical Validity from Semantic Plausibility through Canonical Abstraction",
author = "Faisal, Adnan and
Chowdhury, Shiti",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.70/",
pages = "490--496",
ISBN = "979-8-89176-414-9",
abstract = "Determining whether large language models (LLMs) perform genuine formal reasoning or rely on semantic heuristics is a key challenge in NLP. Syllogistic reasoning constitutes a theoretically principled evaluation paradigm where validity is fully determined by quantifier structure, allowing systematic analysis of structural inference disentangled from semantic plausibility.SemEval-2026 Task-11, Subtask-1: Disentangling Content and Formal Reasoning in Language Models, establishes a multilingual benchmark designed to rigorously isolate formal logical validity from semantic plausibility effects. The subtask evaluates English syllogistic reasoning under a binary classification setting using Overall Accuracy (ACC) and Total Content Effect (TCE), where lower TCE indicates stronger resistance to content-induced bias.Our proposed approach combines cross-validation, structured aggregation and bias-aware evaluation to optimize the robustness{--}performance trade-off. It achieves 93.19{\textbackslash}{\%} accuracy with a TCE of 3.13, yielding a strong combined score of 38.56 under the official evaluation metric. Condition-wise and multi-run analysis confirms that robustness-focused optimization curbs content-driven errors, reinforcing the necessity of bias-aware training for formal inference"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faisal-chowdhury-2026-cuetluminaries">
<titleInfo>
<title>CUETLuminaries at SemEval-2026 Task 11 Disentangling Logical Validity from Semantic Plausibility through Canonical Abstraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adnan</namePart>
<namePart type="family">Faisal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiti</namePart>
<namePart type="family">Chowdhury</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 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>Determining whether large language models (LLMs) perform genuine formal reasoning or rely on semantic heuristics is a key challenge in NLP. Syllogistic reasoning constitutes a theoretically principled evaluation paradigm where validity is fully determined by quantifier structure, allowing systematic analysis of structural inference disentangled from semantic plausibility.SemEval-2026 Task-11, Subtask-1: Disentangling Content and Formal Reasoning in Language Models, establishes a multilingual benchmark designed to rigorously isolate formal logical validity from semantic plausibility effects. The subtask evaluates English syllogistic reasoning under a binary classification setting using Overall Accuracy (ACC) and Total Content Effect (TCE), where lower TCE indicates stronger resistance to content-induced bias.Our proposed approach combines cross-validation, structured aggregation and bias-aware evaluation to optimize the robustness–performance trade-off. It achieves 93.19\textbackslash% accuracy with a TCE of 3.13, yielding a strong combined score of 38.56 under the official evaluation metric. Condition-wise and multi-run analysis confirms that robustness-focused optimization curbs content-driven errors, reinforcing the necessity of bias-aware training for formal inference</abstract>
<identifier type="citekey">faisal-chowdhury-2026-cuetluminaries</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.70/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>490</start>
<end>496</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUETLuminaries at SemEval-2026 Task 11 Disentangling Logical Validity from Semantic Plausibility through Canonical Abstraction
%A Faisal, Adnan
%A Chowdhury, Shiti
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F faisal-chowdhury-2026-cuetluminaries
%X Determining whether large language models (LLMs) perform genuine formal reasoning or rely on semantic heuristics is a key challenge in NLP. Syllogistic reasoning constitutes a theoretically principled evaluation paradigm where validity is fully determined by quantifier structure, allowing systematic analysis of structural inference disentangled from semantic plausibility.SemEval-2026 Task-11, Subtask-1: Disentangling Content and Formal Reasoning in Language Models, establishes a multilingual benchmark designed to rigorously isolate formal logical validity from semantic plausibility effects. The subtask evaluates English syllogistic reasoning under a binary classification setting using Overall Accuracy (ACC) and Total Content Effect (TCE), where lower TCE indicates stronger resistance to content-induced bias.Our proposed approach combines cross-validation, structured aggregation and bias-aware evaluation to optimize the robustness–performance trade-off. It achieves 93.19\textbackslash% accuracy with a TCE of 3.13, yielding a strong combined score of 38.56 under the official evaluation metric. Condition-wise and multi-run analysis confirms that robustness-focused optimization curbs content-driven errors, reinforcing the necessity of bias-aware training for formal inference
%U https://aclanthology.org/2026.semeval-1.70/
%P 490-496
Markdown (Informal)
[CUETLuminaries at SemEval-2026 Task 11 Disentangling Logical Validity from Semantic Plausibility through Canonical Abstraction](https://aclanthology.org/2026.semeval-1.70/) (Faisal & Chowdhury, SemEval 2026)
ACL