@inproceedings{upravitelev-etal-2026-hermeneutichools,
title = "hermeneutichools at {S}em{E}val-2026 Task 4: Multiperspectivity as a Resource for Narrative Similarity Prediction",
author = "Upravitelev, Max and
Solopova, Veronika and
Yang, Jing and
Jakob, Charlott and
Sahitaj, Premtim and
Sahitaj, Ariana and
Schmitt, Vera",
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-1.230/",
pages = "1817--1831",
ISBN = "979-8-89176-414-9",
abstract = "Predicting narrative similarity can be under-stood as an inherently interpretive task: differ-ent, equally valid readings of the same text canproduce divergent interpretations and thus dif-ferent similarity judgments, posing a fundamen-tal challenge for semantic evaluation bench-marks that encode a single ground truth. Ratherthan treating this multiperspectivity as a chal-lenge to overcome, we propose to incorporateit in the decision making process of predic-tive systems. To explore this strategy, we cre-ated an ensemble of 31 LLM personas. Theserange from practitioners following interpretiveframeworks to more intuitive, lay-style charac-ters. Our experiments were conducted on theSemEval-2026 Task 4 dataset, where the sys-tem ranked 13th out of 47 teams and achievedan accuracy score of 0.705. Accuracy improveswith ensemble size, consistent with CondorcetJury Theorem-like dynamics under weakenedindependence. Practitioner personas performworse individually but produce less correlatederrors, yielding larger ensemble gains undermajority voting. Our error analysis reveals aconsistent negative association between gender-focused interpretive vocabulary and accuracyacross all persona categories, suggesting ei-ther attention to dimensions not relevant for thebenchmark or valid interpretations absent fromthe ground truth. This finding underscores theneed for evaluation frameworks that accountfor interpretive plurality."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="upravitelev-etal-2026-hermeneutichools">
<titleInfo>
<title>hermeneutichools at SemEval-2026 Task 4: Multiperspectivity as a Resource for Narrative Similarity Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Upravitelev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronika</namePart>
<namePart type="family">Solopova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Charlott</namePart>
<namePart type="family">Jakob</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Premtim</namePart>
<namePart type="family">Sahitaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariana</namePart>
<namePart type="family">Sahitaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Schmitt</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>Predicting narrative similarity can be under-stood as an inherently interpretive task: differ-ent, equally valid readings of the same text canproduce divergent interpretations and thus dif-ferent similarity judgments, posing a fundamen-tal challenge for semantic evaluation bench-marks that encode a single ground truth. Ratherthan treating this multiperspectivity as a chal-lenge to overcome, we propose to incorporateit in the decision making process of predic-tive systems. To explore this strategy, we cre-ated an ensemble of 31 LLM personas. Theserange from practitioners following interpretiveframeworks to more intuitive, lay-style charac-ters. Our experiments were conducted on theSemEval-2026 Task 4 dataset, where the sys-tem ranked 13th out of 47 teams and achievedan accuracy score of 0.705. Accuracy improveswith ensemble size, consistent with CondorcetJury Theorem-like dynamics under weakenedindependence. Practitioner personas performworse individually but produce less correlatederrors, yielding larger ensemble gains undermajority voting. Our error analysis reveals aconsistent negative association between gender-focused interpretive vocabulary and accuracyacross all persona categories, suggesting ei-ther attention to dimensions not relevant for thebenchmark or valid interpretations absent fromthe ground truth. This finding underscores theneed for evaluation frameworks that accountfor interpretive plurality.</abstract>
<identifier type="citekey">upravitelev-etal-2026-hermeneutichools</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.230/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1817</start>
<end>1831</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T hermeneutichools at SemEval-2026 Task 4: Multiperspectivity as a Resource for Narrative Similarity Prediction
%A Upravitelev, Max
%A Solopova, Veronika
%A Yang, Jing
%A Jakob, Charlott
%A Sahitaj, Premtim
%A Sahitaj, Ariana
%A Schmitt, Vera
%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 upravitelev-etal-2026-hermeneutichools
%X Predicting narrative similarity can be under-stood as an inherently interpretive task: differ-ent, equally valid readings of the same text canproduce divergent interpretations and thus dif-ferent similarity judgments, posing a fundamen-tal challenge for semantic evaluation bench-marks that encode a single ground truth. Ratherthan treating this multiperspectivity as a chal-lenge to overcome, we propose to incorporateit in the decision making process of predic-tive systems. To explore this strategy, we cre-ated an ensemble of 31 LLM personas. Theserange from practitioners following interpretiveframeworks to more intuitive, lay-style charac-ters. Our experiments were conducted on theSemEval-2026 Task 4 dataset, where the sys-tem ranked 13th out of 47 teams and achievedan accuracy score of 0.705. Accuracy improveswith ensemble size, consistent with CondorcetJury Theorem-like dynamics under weakenedindependence. Practitioner personas performworse individually but produce less correlatederrors, yielding larger ensemble gains undermajority voting. Our error analysis reveals aconsistent negative association between gender-focused interpretive vocabulary and accuracyacross all persona categories, suggesting ei-ther attention to dimensions not relevant for thebenchmark or valid interpretations absent fromthe ground truth. This finding underscores theneed for evaluation frameworks that accountfor interpretive plurality.
%U https://aclanthology.org/2026.semeval-1.230/
%P 1817-1831
Markdown (Informal)
[hermeneutichools at SemEval-2026 Task 4: Multiperspectivity as a Resource for Narrative Similarity Prediction](https://aclanthology.org/2026.semeval-1.230/) (Upravitelev et al., SemEval 2026)
ACL
- Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob, Premtim Sahitaj, Ariana Sahitaj, and Vera Schmitt. 2026. hermeneutichools at SemEval-2026 Task 4: Multiperspectivity as a Resource for Narrative Similarity Prediction. In Proceedings of the 20th International Workshop on Semantic Evaluation (2026), pages 1817–1831, San Diego, California, USA. Association for Computational Linguistics.