When Meaning Isn't Literal: Exploring Idiomatic Meaning Across Languages and Modalities

• URL: http://arxiv.org/abs/2604.10787v1
• Date: Sun, 12 Apr 2026 19:36:00 GMT
• Title: When Meaning Isn't Literal: Exploring Idiomatic Meaning Across Languages and Modalities
• Abstract summary: Hintatic reasoning, deeply intertwined with metaphor and culture, remains a blind spot for contemporary language models.<n>We present Mediom,'' a multilingual, multimodal corpus of 3,533 Hindi, Bengali, and Thai idioms.<n>We benchmark both large language models (textual reasoning) and vision-language models (figurative disambiguation) on Mediom, exposing systematic failures in metaphor comprehension.
• Score: 27.883451560702284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Idiomatic reasoning, deeply intertwined with metaphor and culture, remains a blind spot for contemporary language models, whose progress skews toward surface-level lexical and semantic cues. For instance, the Bengali idiom \textit{\foreignlanguage{bengali}{\char"0986\char"0999\char"09CD\char"0997\char"09C1 \char"09B0 \char"09AB\char"09B2 \char"099F\char"0995}} (angur fol tok, ``grapes are sour''): it encodes denial-driven rationalization, yet naive models latch onto the literal fox-and-grape imagery. Addressing this oversight, we present ``Mediom,'' a multilingual, multimodal idiom corpus of 3,533 Hindi, Bengali, and Thai idioms, each paired with gold-standard explanations, cross-lingual translations, and carefully aligned text--image representations. We benchmark both large language models (textual reasoning) and vision-language models (figurative disambiguation) on Mediom, exposing systematic failures in metaphor comprehension. To mitigate these gaps, we propose ``HIDE,'' a Hinting-based Idiom Explanation framework that leverages error-feedback retrieval and targeted diagnostic cues for iterative reasoning refinement. Collectively, Mediom and HIDE establish a rigorous test bed and methodology for culturally grounded, multimodal idiom understanding embedded with reasoning hints in next-generation AI systems.

Related papers

• Calibrated Ambiguity in Multimodal Language Models: Humans reach for cultural references, while models describe the picture [3.7696009147557867]
  We operationalise the notion of calibrated ambiguity with a task drawn from the parlour game Dixit.<n>We compare differences in clues generated by human vs multimodal language models, based on a novel coding rubric for calibrated ambiguity.<n>Unlike human clues, AI-generated clues also exhibit cultural flattening; they almost never make reference to culturally-situated knowledge.
  arXiv  Detail & Related papers  (2026-09-11T08:25:55Z)
• IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions [4.226114812064301]
  We introduce IdioLink, a retrieval benchmark designed to test whether models can link idiomatic expressions to conceptually equivalent meanings expressed in literal or paraphrased forms.<n>IdioLink comprises 10,700 documents and 2,140 queries, spanning 107 idioms with both literal and figurative uses.
  arXiv  Detail & Related papers  (2026-05-21T09:53:10Z)
• IDIOLEX: Unified and Continuous Representations for Idiolectal and Stylistic Variation [88.98544786373212]
  Existing sentence representations primarily encode what a sentence says, rather than how it is expressed.<n>We develop sentence representations that capture style and dialect, decoupled from semantic content.<n>We introduce IDIOLEX, a framework for training models that combines supervision from a sentence's provenance with linguistic features of a sentence's content.
  arXiv  Detail & Related papers  (2026-04-06T14:17:24Z)
• When Words Don't Mean What They Say: Figurative Understanding in Bengali Idioms [1.5840067220859924]
  Figurative language understanding remains a significant challenge for Large Language Models (LLMs)<n>We introduce a new idiom dataset, a large-scale, culturally-grounded corpus of 10,361 Bengali idioms.<n>Each idiom is annotated under a comprehensive 19-field schema, established and refined through a deliberative expert consensus process.<n>We evaluate 30 state-of-the-art multilingual and instruction-tuned LLMs on the task of inferring figurative meaning.
  arXiv  Detail & Related papers  (2026-02-13T13:26:11Z)
• "Newspaper Eat" Means "Not Tasty": A Taxonomy and Benchmark for Coded Languages in Real-World Chinese Online Reviews [14.361987265496042]
  This paper introduces CodedLang, a dataset of 7,744 Chinese Google Maps reviews with span-level annotations of coded language.<n>We developed a seven-class taxonomy that captures common encoding strategies, including phonetic, orthographic, and cross-lingual substitutions.<n>Results show that even strong models can fail to identify or understand coded language.
  arXiv  Detail & Related papers  (2026-01-12T08:03:37Z)
• X-MuTeST: A Multilingual Benchmark for Explainable Hate Speech Detection and A Novel LLM-consulted Explanation Framework [3.3141746520662103]
  We propose a novel explainability-guided training framework, X-MuTeST, for hate speech detection.<n>We extend this research to Hindi and Telugu alongside English by providing benchmark human-annotated rationales.<n>We show that leveraging human rationales during training enhances both classification performance and explainability.
  arXiv  Detail & Related papers  (2026-01-06T17:16:45Z)
• Lost without translation -- Can transformer (language models) understand mood states? [3.640688858400333]
  Methods: We collected 247 unique phrases for the four mood states across 11 Indic languages.<n>Performance was measured using a composite score based on Adjusted Rand Index, Normalised Mutual Information, Homogeneity and Completeness.
  arXiv  Detail & Related papers  (2025-11-29T01:55:11Z)
• Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages [3.2498796510544636]
  Translating multi-word expressions (MWEs) and idioms requires a deep understanding of both the source and target languages.<n>Traditional static knowledge graphs (KGs) and prompt-based approaches struggle to capture these complex relationships.<n>We propose an adaptive graph neural network (GNN) based methodology that learns intricate mappings between idiomatic expressions.
  arXiv  Detail & Related papers  (2025-05-28T03:42:16Z)
• Pixel Sentence Representation Learning [67.4775296225521]
  In this work, we conceptualize the learning of sentence-level textual semantics as a visual representation learning process. We employ visually-grounded text perturbation methods like typos and word order shuffling, resonating with human cognitive patterns, and enabling perturbation to be perceived as continuous. Our approach is further bolstered by large-scale unsupervised topical alignment training and natural language inference supervision.
  arXiv  Detail & Related papers  (2024-02-13T02:46:45Z)
• That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context? [64.38544995251642]
  We study semantic ambiguities that exist in the source (English in this work) itself. We focus on idioms that are open to both literal and figurative interpretations. We find that current MT models consistently translate English idioms literally, even when the context suggests a figurative interpretation.
  arXiv  Detail & Related papers  (2023-10-23T06:38:49Z)
• Transparency Helps Reveal When Language Models Learn Meaning [71.96920839263457]
  Our systematic experiments with synthetic data reveal that, with languages where all expressions have context-independent denotations, both autoregressive and masked language models learn to emulate semantic relations between expressions. Turning to natural language, our experiments with a specific phenomenon -- referential opacity -- add to the growing body of evidence that current language models do not well-represent natural language semantics.
  arXiv  Detail & Related papers  (2022-10-14T02:35:19Z)
• Language Models are Multilingual Chain-of-Thought Reasoners [83.37148309771378]
  We introduce the Multilingual Grade School Math benchmark, by manually translating 250 grade-school math problems into ten typologically diverse languages. We find that the ability to solve MGSM problems via chain-of-thought prompting emerges with increasing model scale. We show that the multilingual reasoning abilities of language models extend to other tasks such as commonsense reasoning and word-in-context semantic judgment.
  arXiv  Detail & Related papers  (2022-10-06T17:03:34Z)
• Testing the Ability of Language Models to Interpret Figurative Language [69.59943454934799]
  Figurative and metaphorical language are commonplace in discourse. It remains an open question to what extent modern language models can interpret nonliteral phrases. We introduce Fig-QA, a Winograd-style nonliteral language understanding task.
  arXiv  Detail & Related papers  (2022-04-26T23:42:22Z)
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand? [87.20342701232869]
  We investigate the abilities of ungrounded systems to acquire meaning. We study whether assertions enable a system to emulate representations preserving semantic relations like equivalence. We find that assertions enable semantic emulation if all expressions in the language are referentially transparent. However, if the language uses non-transparent patterns like variable binding, we show that emulation can become an uncomputable problem.
  arXiv  Detail & Related papers  (2021-04-22T01:00:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.