@inproceedings{biesterbos-etal-2026-rvh,
title = "{R}v{H}-40 at {S}em{E}val-2026 Task 11: Disentangling Reasoning from Belief through Symbolic Abstraction",
author = "Biesterbos, Niek and
Den Ouden, Mark and
De Rijke, Janiek",
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-1.65/",
pages = "451--456",
ISBN = "979-8-89176-414-9",
abstract = "Large Language Models (LLMs) often struggle with syllogistic reasoning due to ``belief bias,'' where semantic world knowledge overrides formal logical structure. In this paper, we present our submission for the SemEval-2026 Task 11 shared task. We investigate the discrepancy between a model{'}s latent logical capabilities and its performance on natural language text. By employing symbolic transformations, specifically variable and pseudoword substitution, we demonstrate that models like Qwen2.5-14B possess strong inherent reasoning skills that are suppressed by linguistic content. We propose a ``logic alignment'' strategy using Low-Rank Adaptation (LoRA) to bridge this gap. Our final model achieved a near-perfect accuracy of 97.92{\%} on the validation set and 96.34{\%} on the official hidden test set, effectively eliminating content bias while maintaining robust generalization across abstract formats."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="biesterbos-etal-2026-rvh">
<titleInfo>
<title>RvH-40 at SemEval-2026 Task 11: Disentangling Reasoning from Belief through Symbolic Abstraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niek</namePart>
<namePart type="family">Biesterbos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Den Ouden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janiek</namePart>
<namePart type="family">De Rijke</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>Large Language Models (LLMs) often struggle with syllogistic reasoning due to “belief bias,” where semantic world knowledge overrides formal logical structure. In this paper, we present our submission for the SemEval-2026 Task 11 shared task. We investigate the discrepancy between a model’s latent logical capabilities and its performance on natural language text. By employing symbolic transformations, specifically variable and pseudoword substitution, we demonstrate that models like Qwen2.5-14B possess strong inherent reasoning skills that are suppressed by linguistic content. We propose a “logic alignment” strategy using Low-Rank Adaptation (LoRA) to bridge this gap. Our final model achieved a near-perfect accuracy of 97.92% on the validation set and 96.34% on the official hidden test set, effectively eliminating content bias while maintaining robust generalization across abstract formats.</abstract>
<identifier type="citekey">biesterbos-etal-2026-rvh</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.65/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>451</start>
<end>456</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RvH-40 at SemEval-2026 Task 11: Disentangling Reasoning from Belief through Symbolic Abstraction
%A Biesterbos, Niek
%A Den Ouden, Mark
%A De Rijke, Janiek
%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 biesterbos-etal-2026-rvh
%X Large Language Models (LLMs) often struggle with syllogistic reasoning due to “belief bias,” where semantic world knowledge overrides formal logical structure. In this paper, we present our submission for the SemEval-2026 Task 11 shared task. We investigate the discrepancy between a model’s latent logical capabilities and its performance on natural language text. By employing symbolic transformations, specifically variable and pseudoword substitution, we demonstrate that models like Qwen2.5-14B possess strong inherent reasoning skills that are suppressed by linguistic content. We propose a “logic alignment” strategy using Low-Rank Adaptation (LoRA) to bridge this gap. Our final model achieved a near-perfect accuracy of 97.92% on the validation set and 96.34% on the official hidden test set, effectively eliminating content bias while maintaining robust generalization across abstract formats.
%U https://aclanthology.org/2026.semeval-1.65/
%P 451-456
Markdown (Informal)
[RvH-40 at SemEval-2026 Task 11: Disentangling Reasoning from Belief through Symbolic Abstraction](https://aclanthology.org/2026.semeval-1.65/) (Biesterbos et al., SemEval 2026)
ACL