@inproceedings{schneidermann-etal-2026-dameta,
title = "{DAMETA}: An {LLM} Benchmark for {D}anish Metaphor Interpretation with Systematically Varied Distractors",
author = "Schneidermann, Nina Skovgaard and
Nimb, Sanni and
Norman, Nathalie Carmen Hau and
Olsen, Sussi and
Pedersen, Bolette",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.930/",
doi = "10.63317/5myuqkhnpm7e",
pages = "11885--11895",
abstract = "We present DAMETA, the first evaluation benchmark for Danish metaphor interpretation in language models, derived from the following sources: an annotated corpus (the Dafig Corpus), the Danish dictionary (DDO) and culture reviews in Danish newspapers. Each of the 900 data instances contains a sentence with a metaphorical target word and four human-created paraphrase options; one correct interpretation and three systematic errors or distractors: i) a false literal paraphrase (typically concrete), ii) a false figurative paraphrase (typically abstract), and iii) a false contradictory paraphrase. The benchmark is tested on seven language models, and 5{\%} of the data is further tested on humans for comparison. Results show, among others, that when informed in the prompt that the target word is a metaphor, the models tend to be most distracted by the false figurative paraphrase; in contrast, when uninformed about the metaphorical setting, the models are more distracted by the false literal paraphrase. The dataset goes beyond standard by incorporating descriptive metadata regarding metaphor conventionality on a 3-graded scale (lexicalised, implicit, and ad-hoc), alongside a range of dictionary-derived source domains (military, gastronomy, health, meteorology, etc.). These metadata enable deeper analysis and potentially innovative insights of model performance regarding creativity, language change, and culture-sensitivity."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schneidermann-etal-2026-dameta">
<titleInfo>
<title>DAMETA: An LLM Benchmark for Danish Metaphor Interpretation with Systematically Varied Distractors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="given">Skovgaard</namePart>
<namePart type="family">Schneidermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanni</namePart>
<namePart type="family">Nimb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathalie</namePart>
<namePart type="given">Carmen</namePart>
<namePart type="given">Hau</namePart>
<namePart type="family">Norman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sussi</namePart>
<namePart type="family">Olsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bolette</namePart>
<namePart type="family">Pedersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present DAMETA, the first evaluation benchmark for Danish metaphor interpretation in language models, derived from the following sources: an annotated corpus (the Dafig Corpus), the Danish dictionary (DDO) and culture reviews in Danish newspapers. Each of the 900 data instances contains a sentence with a metaphorical target word and four human-created paraphrase options; one correct interpretation and three systematic errors or distractors: i) a false literal paraphrase (typically concrete), ii) a false figurative paraphrase (typically abstract), and iii) a false contradictory paraphrase. The benchmark is tested on seven language models, and 5% of the data is further tested on humans for comparison. Results show, among others, that when informed in the prompt that the target word is a metaphor, the models tend to be most distracted by the false figurative paraphrase; in contrast, when uninformed about the metaphorical setting, the models are more distracted by the false literal paraphrase. The dataset goes beyond standard by incorporating descriptive metadata regarding metaphor conventionality on a 3-graded scale (lexicalised, implicit, and ad-hoc), alongside a range of dictionary-derived source domains (military, gastronomy, health, meteorology, etc.). These metadata enable deeper analysis and potentially innovative insights of model performance regarding creativity, language change, and culture-sensitivity.</abstract>
<identifier type="citekey">schneidermann-etal-2026-dameta</identifier>
<identifier type="doi">10.63317/5myuqkhnpm7e</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.930/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11885</start>
<end>11895</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DAMETA: An LLM Benchmark for Danish Metaphor Interpretation with Systematically Varied Distractors
%A Schneidermann, Nina Skovgaard
%A Nimb, Sanni
%A Norman, Nathalie Carmen Hau
%A Olsen, Sussi
%A Pedersen, Bolette
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F schneidermann-etal-2026-dameta
%X We present DAMETA, the first evaluation benchmark for Danish metaphor interpretation in language models, derived from the following sources: an annotated corpus (the Dafig Corpus), the Danish dictionary (DDO) and culture reviews in Danish newspapers. Each of the 900 data instances contains a sentence with a metaphorical target word and four human-created paraphrase options; one correct interpretation and three systematic errors or distractors: i) a false literal paraphrase (typically concrete), ii) a false figurative paraphrase (typically abstract), and iii) a false contradictory paraphrase. The benchmark is tested on seven language models, and 5% of the data is further tested on humans for comparison. Results show, among others, that when informed in the prompt that the target word is a metaphor, the models tend to be most distracted by the false figurative paraphrase; in contrast, when uninformed about the metaphorical setting, the models are more distracted by the false literal paraphrase. The dataset goes beyond standard by incorporating descriptive metadata regarding metaphor conventionality on a 3-graded scale (lexicalised, implicit, and ad-hoc), alongside a range of dictionary-derived source domains (military, gastronomy, health, meteorology, etc.). These metadata enable deeper analysis and potentially innovative insights of model performance regarding creativity, language change, and culture-sensitivity.
%R 10.63317/5myuqkhnpm7e
%U https://aclanthology.org/2026.lrec-1.930/
%U https://doi.org/10.63317/5myuqkhnpm7e
%P 11885-11895
Markdown (Informal)
[DAMETA: An LLM Benchmark for Danish Metaphor Interpretation with Systematically Varied Distractors](https://aclanthology.org/2026.lrec-1.930/) (Schneidermann et al., LREC 2026)
ACL