@inproceedings{buyukbas-etal-2026-sabancigroup4,
title = "Sabancigroup4 at {S}em{E}val-2026 Task 5: Uncertainty-Aware Semantic Plausibility Scoring via {GNLL} Regression and {LLM} Rationales",
author = {B{\"u}y{\"u}kba{\c{s}}, Salih and
Benli, Doruk and
Kara, Osman and
Kek{\"u}ll{\"u}o{\u{g}}lu, Dilara},
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-1.144/",
pages = "1056--1062",
ISBN = "979-8-89176-414-9",
abstract = "SemEval-2026 Task 5 is a shared task on rating the plausibility of an ambiguous homonym in a predetermined context. The dataset of this task consists of a precontext {\&} sentence {\&} ending combinations for each homonym, and the plausibility of the sample is manually rated by 5 annotators. The task of participating teams was to automatically predict the plausibility with respect to the mean rate given by the annotators. Unlike traditional models that rely on single-label selection, this task frames disambiguation as a probabilistic distribution over multiple plausible meanings. To this end, we propose an uncertainty-aware training strategy using GNLL regression, and semantic context enrichment through POS tags and LLM rationales. Our system exhibits competitive performance, achieving 90{\%} accuracy within standard deviation and 81{\%} Spearman correlation, and placing us in the ninth place in the leaderboard."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="buyukbas-etal-2026-sabancigroup4">
<titleInfo>
<title>Sabancigroup4 at SemEval-2026 Task 5: Uncertainty-Aware Semantic Plausibility Scoring via GNLL Regression and LLM Rationales</title>
</titleInfo>
<name type="personal">
<namePart type="given">Salih</namePart>
<namePart type="family">Büyükbaş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doruk</namePart>
<namePart type="family">Benli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Osman</namePart>
<namePart type="family">Kara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilara</namePart>
<namePart type="family">Keküllüoğlu</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>SemEval-2026 Task 5 is a shared task on rating the plausibility of an ambiguous homonym in a predetermined context. The dataset of this task consists of a precontext & sentence & ending combinations for each homonym, and the plausibility of the sample is manually rated by 5 annotators. The task of participating teams was to automatically predict the plausibility with respect to the mean rate given by the annotators. Unlike traditional models that rely on single-label selection, this task frames disambiguation as a probabilistic distribution over multiple plausible meanings. To this end, we propose an uncertainty-aware training strategy using GNLL regression, and semantic context enrichment through POS tags and LLM rationales. Our system exhibits competitive performance, achieving 90% accuracy within standard deviation and 81% Spearman correlation, and placing us in the ninth place in the leaderboard.</abstract>
<identifier type="citekey">buyukbas-etal-2026-sabancigroup4</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.144/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1056</start>
<end>1062</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Sabancigroup4 at SemEval-2026 Task 5: Uncertainty-Aware Semantic Plausibility Scoring via GNLL Regression and LLM Rationales
%A Büyükbaş, Salih
%A Benli, Doruk
%A Kara, Osman
%A Keküllüoğlu, Dilara
%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 buyukbas-etal-2026-sabancigroup4
%X SemEval-2026 Task 5 is a shared task on rating the plausibility of an ambiguous homonym in a predetermined context. The dataset of this task consists of a precontext & sentence & ending combinations for each homonym, and the plausibility of the sample is manually rated by 5 annotators. The task of participating teams was to automatically predict the plausibility with respect to the mean rate given by the annotators. Unlike traditional models that rely on single-label selection, this task frames disambiguation as a probabilistic distribution over multiple plausible meanings. To this end, we propose an uncertainty-aware training strategy using GNLL regression, and semantic context enrichment through POS tags and LLM rationales. Our system exhibits competitive performance, achieving 90% accuracy within standard deviation and 81% Spearman correlation, and placing us in the ninth place in the leaderboard.
%U https://aclanthology.org/2026.semeval-1.144/
%P 1056-1062
Markdown (Informal)
[Sabancigroup4 at SemEval-2026 Task 5: Uncertainty-Aware Semantic Plausibility Scoring via GNLL Regression and LLM Rationales](https://aclanthology.org/2026.semeval-1.144/) (Büyükbaş et al., SemEval 2026)
ACL