mlsanityData to 14 Oct 2026

Multi-lingual and Multi-cultural Figurative Language Understanding

arXiv 2305.16171 ↗First posted 25 May 2023cs.CLcited by 47

Not on the map. Why?

Abstract (arXiv)

Figurative language permeates human communication, but at the same time is relatively understudied in NLP. Datasets have been created in English to accelerate progress towards measuring and improving figurative language processing in language models (LMs). However, the use of figurative language is an expression of our cultural and societal experiences, making it difficult for these phrases to be universally applicable. In this work, we create a figurative language inference dataset, datasetname, for seven diverse languages associated with a variety of cultures: Hindi, Indonesian, Javanese, Kannada, Sundanese, Swahili and Yoruba. Our dataset reveals that each language relies on cultural and regional concepts for figurative expressions, with the highest overlap between languages originating from the same region. We assess multilingual LMs' abilities to interpret figurative language in zero-shot and few-shot settings. All languages exhibit a significant deficiency compared to English, with variations in performance reflecting the availability of pre-training and fine-tuning data, emphasizing the need for LMs to be exposed to a broader range of linguistic and cultural variation during training.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Builds on 18 of its 44 references that are in the map. First posted on arXiv 25 May 2023.

Builds on

18 of 44 references.

References · 18

  1. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  2. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  3. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  4. 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 445
  5. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  6. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 217
  7. 2021Visually Grounded Reasoning across Languages and Culturescited by 189
  8. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 144
  9. 2022FLUTE: Figurative Language Understanding through Textual Explanationscited by 79
  10. 2022Testing the Ability of Language Models to Interpret Figurative Languagecited by 67
  11. 2022One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesiacited by 66
  12. 2021The paradox of the compositionality of natural language: a neural machine translation case studycited by 59
6 more
  1. 2018Challenges for Toxic Comment Classification: An In-Depth Error Analysiscited by 56
  2. 2020From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformerscited by 35
  3. 2022Metaphors in Pre-Trained Language Models: Probing and Generalization Across Datasets and Languagescited by 30
  4. 2021Role of Language Relatedness in Multilingual Fine-tuning of Language Models: A Case Study in Indo-Aryan Languagescited by 24
  5. 2021Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledgecited by 15
  6. 2021Towards More Equitable Question Answering Systems: How Much More Data Do You Need?cited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 5; 2024: 19; 2025: 13; 2026: 10.

47 papers.

Sort:

By area:

  1. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 452
  2. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 167
  3. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmarkcited by 120
  4. 2024LLMs Are Few-Shot In-Context Low-Resource Language Learnerscited by 68
  5. 2024Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontierscited by 51
  6. 2024SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languagescited by 43
  7. 2025Culture is Not Trivia: Sociocultural Theory for Cultural NLPcited by 40
  8. 2024WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisinescited by 39
  9. 2023Are Multilingual LLMs Culturally-Diverse Reasoners? An Investigation into Multicultural Proverbs and Sayingscited by 32
  10. 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Artcited by 26
  11. 2024Extrinsic Evaluation of Cultural Competence in Large Language Modelscited by 24
  12. 2024Cultural Conditioning or Placebo? On the Effectiveness of Socio-Demographic Promptingcited by 22
35 more
  1. 2025SEA-HELM: Southeast Asian Holistic Evaluation of Language Modelscited by 19
  2. 2024Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveyscited by 18
  3. 2024Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languagescited by 18
  4. 2025Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarkingcited by 18
  5. 2024From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Modelscited by 14
  6. 2024mCSQA: Multilingual Commonsense Reasoning Dataset with Unified Creation Strategy by Language Models and Humanscited by 10
  7. 2025The Multilingual Divide and Its Impact on Global AI Safetycited by 10
  8. 2023CPopQA: Ranking Cultural Concept Popularity by LLMscited by 8
  9. 2024How Well Do LLMs Identify Cultural Unity in Diversity?cited by 8
  10. 2025Metaphor and Large Language Models: When Surface Features Matter More than Deep Understandingcited by 8
  11. 2023NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languagescited by 5
  12. 2023InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systemscited by 5
  13. 2024Meta4XNLI: A Crosslingual Parallel Corpus for Metaphor Detection and Interpretationcited by 5
  14. 2024Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sensecited by 4
  15. 2025Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gesturescited by 4
  16. 2025Isolating Culture Neurons in Multilingual Large Language Modelscited by 4
  17. 2023That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?cited by 3
  18. 2025Tug-of-war between idioms' figurative and literal interpretations in LLMscited by 3
  19. 2025Let's Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models' Understanding of Sportscited by 3
  20. 2025Assessing Socio-Cultural Alignment and Technical Safety of Sovereign LLMscited by 2
  21. 2026FFE-Hallu:Hallucinations in Fixed Figurative Expressions:Benchmark of Idioms and Proverbs in the Persian Languagecited by 2
  22. 2026Anthropogenic Regional Adaptation in Multimodal Vision-Language Modelcited by 2
  23. 2024Is the Pope Catholic? Yes, the Pope is Catholic. Generative Evaluation of Non-Literal Intent Resolution in LLMscited by 1
  24. 2025Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Modelscited by 1
  25. 2025Adaptive Originality Filtering: Rejection Based Prompting and RiddleScore for Culturally Grounded Multilingual Riddle Generationcited by 1
  26. 2026SinFoS: A Parallel Dataset for Translating Sinhala Figures of Speechcited by 1
  27. 2024Large Language Models for Persian leftrightarrow English Idiom Translationcited by 0
  28. 2025Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Languagecited by 0
  29. 2026NRITYAM: Language Models Meet Art and Heritage of Dancecited by 0
  30. 2026Towards High-Level Semantic Intelligencecited by 0
  31. 2026Wisdom in Unity: The Role of Multilingual Training in Figurative Language Identification in Proverbscited by 0
  32. 2026Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuningcited by 0
  33. 2026MemeBridge: A Dataset for Benchmarking and Mitigating the Bidirectional Cultural Gap in Meme Interpretationcited by 0
  34. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0
  35. 2026Supporting and Performing Culture from the Insidecited by 0