Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages

ACL ARR 2026 January Submission10011 Authors

Keywords: idioms, multilingual NLP, low-resource languages, languages, dialects, figurative language, multilingual evaluation, contextual reasoning, representation steering, memorization, reasoning, dataset, memorization vs reasoning, literal interpretation, interpretation bias, large language models

Abstract: Idiomatic expressions pose a major challenge for multilingual NLP because their meanings shift between figurative and literal usage, often requiring context for accurate interpretation. Prior work has focused on high-resource languages typically evaluates isolated idiom-meaning questions, overlooking realistic discourse. We introduce MIDI, a multilingual idiom dataset spanning 3 high-, 3 medium-, and 12 low-resource languages, curated by native speakers. Unlike previous datasets, MIDI provides idioms embedded in both sentence-level and conversational contexts, capturing both literal and figurative readings. Benchmarking state-of-the-art models shows that idiom comprehension degrades in low-resource languages and that, in all resource tiers, literal interpretations are substantially harder than figurative ones. Conversational context improves performance but does not eliminate these disparities. Through controlled tests and interventions on hidden representations, we further separate memorization from reasoning, exposing core limitations of current models.

Paper Type: Long

Research Area: Multilinguality and Language Diversity

Research Area Keywords: multilingual / low resource, language/cultural bias analysis, computational psycholinguistics, multilingual benchmarks, less-resourced languages, datasets for low resource languages, reasoning

Contribution Types: Model analysis & interpretability, Data resources, Data analysis

Languages Studied: Javanese, Persian, Kannada, Telugu, Tamil, Minangkabau, Sundanese, Kazakh, Yoruba, Arabic, Indonesian, Vietnamese, Chinese, Japanese, Russian

Submission Number: 10011