Skip to content
Review

DAMETA: An LLM Benchmark for Danish Metaphor Interpretation with Systematically Varied Distractors

2026 · International Conference on Language Resources and Evaluation · pp. 11885-11895 · 0 citations · 24 references
Computer Science

TL;DR

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.

View source

Similar papers

Open access Sep 2026

Working memory and vocabulary knowledge sustain activation of the literal meaning of metaphors during sentence comprehension.

Metaphors convey meanings beyond their literal interpretation, requiring individuals to rely on linguistic and cognitive resources beyond those used for literal language. Models of metaphor comprehension propose different routes to deriving metaphorical content. The indirect-access model suggests that literal meaning i...

Laura Pissani, M. Scholman, Vera Demberg · 3 citations
Open access Sep 2026

Systematicity and Evidential Density in a Corpus-Based Conceptual Metaphor Dictionary of J. R. R. Tolkien’s The Lord of the Rings

Conceptual Metaphor Theory holds that metaphor is systematic: a single cross-domain mapping licenses many linguistic expressions. This claim is routinely invoked in literary metaphor scholarship but rarely tested against the evidence that individual studies actually assemble. The present study reports a corpus-based co...

Abdulxay Qosimov · 0 citations
Open access Oct 2026

Universal patterns in the acquisition of negation and disjunction: Parallels between L1 and L2.

A fundamental question in language acquisition is how learners balance input and prior knowledge to infer meaning. Here, we present novel evidence about the mechanisms guiding adults' second language learning. We examined their interpretation of disjunction ("or") in negative sentences (e.g., "John didn't eat the cucum...

E. Pagliarini, Jin Yan, Anna Gavarró · 0 citations
#natural language process... Conference Open access Sep 2026

Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension

This work systematically vary the context window size of GPT-2 across four large-scale naturalistic English reading-time datasets and observes a U-shaped relationship, demonstrating that tracking long-range coreference relations is one important factor for the alignment between LM surprisal and human reading behavior.

Kohei Kajikawa, Lin Ai, Tatsuki Kuribayashi et al. · 0 citations
Open access Oct 2026

Decoding Figurative Language in Journalism Translation: Human and LLM Translation of English-Vietnamese Metaphors

The increasing use of large language models (LLMs) in professional translation has reshaped multilingual news production. While prior research has reported gains in fluency and surface-level accuracy, limited attention has been paid to LLMs’ ability to translate figurative language, which plays a key role in meaning co...

Phuong Luong, Huong Thi Thanh Nguyen, V. Tran · 0 citations

From annotation to reasoning: Culture in language models

This work argues that literary interpretation offers a useful setting for studying cultural referencing and reuse: how texts invoke, repeat, and transform earlier expressions across historical and linguistic contexts and proposes linking evidence-centered benchmarks, evaluation that preserves scholarly disagreement, an...

Daniel Hershcovich, Alexander Conroy, Jens Bjerring-Hansen · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.