mlsanityData to 14 Oct 2026

Towards Style Alignment in Cross-Cultural Translation

arXiv 2507.00216 ↗First posted 30 Jun 2025cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Successful communication depends on the speaker's intended style (i.e., what the speaker is trying to convey) aligning with the listener's interpreted style (i.e., what the listener perceives). However, cultural differences often lead to misalignment between the two; for example, politeness is often lost in translation. We characterize the ways that LLMs fail to translate style - biasing translations towards neutrality and performing worse in non-Western languages. We mitigate these failures with RASTA (Retrieval-Augmented STylistic Alignment), a method that leverages learned stylistic concepts to encourage LLM translation to appropriately convey cultural communication norms and align style.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 25 of its 58 references that are in the map. First posted on arXiv 30 Jun 2025.

Builds on

25 of 58 references.

References · 25

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  5. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  6. 2022Challenges and Strategies in Cross-Cultural NLPcited by 218
  7. 2018Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfercited by 211
  8. 2022CometKiwi: IST-Unbabel 2022 Submission for the Quality Estimation Shared Taskcited by 207
  9. 2022In-context Examples Selection for Machine Translationcited by 172
  10. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  11. 2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
  12. 2021XFORMAL: A Benchmark for Multilingual Formality Style Transfercited by 52
13 more
  1. 2020TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restylingcited by 40
  2. 2018Multi-Task Neural Models for Translating Between Styles Within and Across Languagescited by 28
  3. 2022CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formalitycited by 24
  4. 2023Translate Meanings, Not Just Words: IdiomKB's Role in Optimizing Idiomatic Translation with Language Modelscited by 24
  5. 2024Towards Cross-Cultural Machine Translation with Retrieval-Augmented Generation from Multilingual Knowledge Graphscited by 22
  6. 2021Few-shot Controllable Style Transfer for Low-Resource Multilingual Settingscited by 21
  7. 2022TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languagescited by 21
  8. 2022FRMT: A Benchmark for Few-Shot Region-Aware Machine Translationcited by 18
  9. 2022Controlling Translation Formality Using Pre-trained Multilingual Language Modelscited by 14
  10. 2022SemEval 2023 Task 9: Multilingual Tweet Intimacy Analysiscited by 14
  11. 2024Multilingual Text Style Transfer: Datasets & Models for Indian Languagescited by 9
  12. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledgecited by 9
  13. 2021Towards Universality in Multilingual Text Rewritingcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Culturally-Aware Conversations: A Framework & Benchmark for LLMscited by 5
  2. 2025VideoNorms: Benchmarking Cultural Awareness of Video Language Modelscited by 4
  3. 2025Semantic Label Drift in Cross-Cultural Translationcited by 2
  4. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026AlignCultura: Towards Culturally Aligned Large Language Models?
  2. 2025Break the Checkbox: Challenging Closed-Style Evaluations of Cultural Alignment in LLMs
  3. 2026Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
  4. 2026Interpretable Cross-Lingual Alignment in Small Language Models: Probing Cultural and Pragmatic Reasoning in Japanese-English Bilingual LLMs
  5. 2025Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs
  6. 2026CoCoA: Context-Conditional Cultural Alignment for Large Language Models
  7. 2026Pak3H: Evaluating the Cost of Cultural Mismatch in LLM Alignment with a Human-Contextualized Urdu Benchmark
  8. 2025Localized Cultural Knowledge is Conserved and Controllable in Large Language Models