@inproceedings{wang-etal-2026-ynu,
title = "{YNU}-{NLP} at {S}em{E}val-2026 Task 11: A Neuro-Symbolic Approach with Reflexion Mechanism Disentangling Content and Formal Reasoning in Language Models",
author = "Wang, Yu and
Zhang, You and
Zhang, Hao and
Xu, Dan",
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-1.126/",
pages = "919--926",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our systems for SemEval-2026 Task 11, Disentangling Content and Formal Reasoning in Language Models. We participated in all four subtasks, addressing the Content Effect-a phenomenon where models rely on real-world plausibility rather than logical validity. Existing methods, such as standard Chain-of-Thought (CoT) prompting or single-task Supervised Fine-Tuning (SFT), often struggle to completely decouple content from reasoning due to the inherent probabilistic biases in pre-trained models. To address these limitations, a hybrid neuro-symbolic framework based on the Qwen2.5-14B architecture is proposed, integrating multi-task instruction tuning with a robust neuro-symbolic pipeline. The principal innovation lies in the deployment of a Reflexion mechanism coupled with formal verification: natural language arguments are parsed into First-Order Logic (FOL) and subsequently verified by the Z3 Theorem Prover. Parsing anomalies are automatically rectified through an iterative self-correction module. The proposed system ranked 1st in Subtasks 1 {\&} 2, 2nd in Subtask 4, and 9th in Subtask 3, validating its ability to decouple logical validity from content plausibility."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-ynu">
<titleInfo>
<title>YNU-NLP at SemEval-2026 Task 11: A Neuro-Symbolic Approach with Reflexion Mechanism Disentangling Content and Formal Reasoning in Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">You</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Xu</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>This paper describes our systems for SemEval-2026 Task 11, Disentangling Content and Formal Reasoning in Language Models. We participated in all four subtasks, addressing the Content Effect-a phenomenon where models rely on real-world plausibility rather than logical validity. Existing methods, such as standard Chain-of-Thought (CoT) prompting or single-task Supervised Fine-Tuning (SFT), often struggle to completely decouple content from reasoning due to the inherent probabilistic biases in pre-trained models. To address these limitations, a hybrid neuro-symbolic framework based on the Qwen2.5-14B architecture is proposed, integrating multi-task instruction tuning with a robust neuro-symbolic pipeline. The principal innovation lies in the deployment of a Reflexion mechanism coupled with formal verification: natural language arguments are parsed into First-Order Logic (FOL) and subsequently verified by the Z3 Theorem Prover. Parsing anomalies are automatically rectified through an iterative self-correction module. The proposed system ranked 1st in Subtasks 1 & 2, 2nd in Subtask 4, and 9th in Subtask 3, validating its ability to decouple logical validity from content plausibility.</abstract>
<identifier type="citekey">wang-etal-2026-ynu</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.126/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>919</start>
<end>926</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T YNU-NLP at SemEval-2026 Task 11: A Neuro-Symbolic Approach with Reflexion Mechanism Disentangling Content and Formal Reasoning in Language Models
%A Wang, Yu
%A Zhang, You
%A Zhang, Hao
%A Xu, Dan
%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 wang-etal-2026-ynu
%X This paper describes our systems for SemEval-2026 Task 11, Disentangling Content and Formal Reasoning in Language Models. We participated in all four subtasks, addressing the Content Effect-a phenomenon where models rely on real-world plausibility rather than logical validity. Existing methods, such as standard Chain-of-Thought (CoT) prompting or single-task Supervised Fine-Tuning (SFT), often struggle to completely decouple content from reasoning due to the inherent probabilistic biases in pre-trained models. To address these limitations, a hybrid neuro-symbolic framework based on the Qwen2.5-14B architecture is proposed, integrating multi-task instruction tuning with a robust neuro-symbolic pipeline. The principal innovation lies in the deployment of a Reflexion mechanism coupled with formal verification: natural language arguments are parsed into First-Order Logic (FOL) and subsequently verified by the Z3 Theorem Prover. Parsing anomalies are automatically rectified through an iterative self-correction module. The proposed system ranked 1st in Subtasks 1 & 2, 2nd in Subtask 4, and 9th in Subtask 3, validating its ability to decouple logical validity from content plausibility.
%U https://aclanthology.org/2026.semeval-1.126/
%P 919-926
Markdown (Informal)
[YNU-NLP at SemEval-2026 Task 11: A Neuro-Symbolic Approach with Reflexion Mechanism Disentangling Content and Formal Reasoning in Language Models](https://aclanthology.org/2026.semeval-1.126/) (Wang et al., SemEval 2026)
ACL