@inproceedings{antonelli-dziri-etal-2026-guysllm,
title = "{G}uys{LLM} at {S}em{E}val-2026 Task 5: {NLI}-Informed Regression for Graded Word-Sense Plausibility in Narrative Contexts",
author = "Antonelli-Dziri, Niccol{\'o} and
Marcotte, Sixtine and
Rosapepe, Emanuele and
Santona, Gabriele and
Wafaay, Omar and
Vaiani, Lorenzo and
Coppola, Riccardo and
Giobergia, Flavio",
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-1.314/",
pages = "2487--2494",
ISBN = "979-8-89176-414-9",
abstract = "While large language models (LLMs) excel at semantic reasoning, their discrete token-based outputs introduce limitations for fine-grained regression tasks requiring continuous scoring. We address graded word-sense plausibility estimation by reformulating it as a Natural Language Inference (NLI) regression problem, adapting DeBERTa-v3-large with NLI pretraining and a regression head to predict continuous plausibility scores from story-sense pairs. We compare this model against BERT, vanilla DeBERTa, SmolLM variants and state-of-the art LLMs under various prompting strategies, and show that the NLI-finetuned model achieves superior rank correlation and alignment with human judgments. While several baselines collapse toward mean predictions and LLMs show unstable prompting sensitivity, our findings establish NLI-informed pretraining as highly effective for narrative plausibility regression, highlighting fundamental LLM limitations for word sense disambiguation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="antonelli-dziri-etal-2026-guysllm">
<titleInfo>
<title>GuysLLM at SemEval-2026 Task 5: NLI-Informed Regression for Graded Word-Sense Plausibility in Narrative Contexts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niccoló</namePart>
<namePart type="family">Antonelli-Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sixtine</namePart>
<namePart type="family">Marcotte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emanuele</namePart>
<namePart type="family">Rosapepe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Santona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Wafaay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenzo</namePart>
<namePart type="family">Vaiani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riccardo</namePart>
<namePart type="family">Coppola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flavio</namePart>
<namePart type="family">Giobergia</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>While large language models (LLMs) excel at semantic reasoning, their discrete token-based outputs introduce limitations for fine-grained regression tasks requiring continuous scoring. We address graded word-sense plausibility estimation by reformulating it as a Natural Language Inference (NLI) regression problem, adapting DeBERTa-v3-large with NLI pretraining and a regression head to predict continuous plausibility scores from story-sense pairs. We compare this model against BERT, vanilla DeBERTa, SmolLM variants and state-of-the art LLMs under various prompting strategies, and show that the NLI-finetuned model achieves superior rank correlation and alignment with human judgments. While several baselines collapse toward mean predictions and LLMs show unstable prompting sensitivity, our findings establish NLI-informed pretraining as highly effective for narrative plausibility regression, highlighting fundamental LLM limitations for word sense disambiguation.</abstract>
<identifier type="citekey">antonelli-dziri-etal-2026-guysllm</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.314/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2487</start>
<end>2494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GuysLLM at SemEval-2026 Task 5: NLI-Informed Regression for Graded Word-Sense Plausibility in Narrative Contexts
%A Antonelli-Dziri, Niccoló
%A Marcotte, Sixtine
%A Rosapepe, Emanuele
%A Santona, Gabriele
%A Wafaay, Omar
%A Vaiani, Lorenzo
%A Coppola, Riccardo
%A Giobergia, Flavio
%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 antonelli-dziri-etal-2026-guysllm
%X While large language models (LLMs) excel at semantic reasoning, their discrete token-based outputs introduce limitations for fine-grained regression tasks requiring continuous scoring. We address graded word-sense plausibility estimation by reformulating it as a Natural Language Inference (NLI) regression problem, adapting DeBERTa-v3-large with NLI pretraining and a regression head to predict continuous plausibility scores from story-sense pairs. We compare this model against BERT, vanilla DeBERTa, SmolLM variants and state-of-the art LLMs under various prompting strategies, and show that the NLI-finetuned model achieves superior rank correlation and alignment with human judgments. While several baselines collapse toward mean predictions and LLMs show unstable prompting sensitivity, our findings establish NLI-informed pretraining as highly effective for narrative plausibility regression, highlighting fundamental LLM limitations for word sense disambiguation.
%U https://aclanthology.org/2026.semeval-1.314/
%P 2487-2494
Markdown (Informal)
[GuysLLM at SemEval-2026 Task 5: NLI-Informed Regression for Graded Word-Sense Plausibility in Narrative Contexts](https://aclanthology.org/2026.semeval-1.314/) (Antonelli-Dziri et al., SemEval 2026)
ACL
- Niccoló Antonelli-Dziri, Sixtine Marcotte, Emanuele Rosapepe, Gabriele Santona, Omar Wafaay, Lorenzo Vaiani, Riccardo Coppola, and Flavio Giobergia. 2026. GuysLLM at SemEval-2026 Task 5: NLI-Informed Regression for Graded Word-Sense Plausibility in Narrative Contexts. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 2487–2494, San Diego, California, USA. Association for Computational Linguistics.