mlsanityData to 14 Oct 2026

CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis

arXiv 2505.19484 ↗First posted 26 May 2025cs.CLcited by 15

On the map: Synthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they often exhibit a specific cultural biases, neglecting the values and linguistic diversity of low-resource regions. This cultural bias not only undermines universal equality, but also risks reinforcing stereotypes and perpetuating discrimination. To address this, we propose CulFiT, a novel culturally-aware training paradigm that leverages multilingual data and fine-grained reward modeling to enhance cultural sensitivity and inclusivity. Our approach synthesizes diverse cultural-related questions, constructs critique data in culturally relevant languages, and employs fine-grained rewards to decompose cultural texts into verifiable knowledge units for interpretable evaluation. We also introduce GlobalCultureQA, a multilingual open-ended question-answering dataset designed to evaluate culturally-aware responses in a global context. Extensive experiments on three existing benchmarks and our GlobalCultureQA demonstrate that CulFiT achieves state-of-the-art open-source model performance in cultural alignment and general reasoning.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Synthetic reasoning data and bootstrapping, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 22 of its 34 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

22 of 34 references.

References · 22

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  5. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  6. 2018CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledgecited by 1,822
  7. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  8. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 783
  9. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 240
  10. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 173
  11. 2024Investigating Cultural Alignment of Large Language Modelscited by 143
  12. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
10 more
  1. 2024Survey of Cultural Awareness in Language Models: Text and Beyondcited by 103
  2. 2023SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoningcited by 94
  3. 2022Extracting Cultural Commonsense Knowledge at Scalecited by 76
  4. 2024CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Promptingcited by 55
  5. 2024Understanding the Capabilities and Limitations of Large Language Models for Cultural Commonsensecited by 51
  6. 2023Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysiscited by 45
  7. 2024Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanesecited by 36
  8. 2024CulturalTeaming: AI-Assisted Interactive Red-Teaming for Challenging LLMs' (Lack of) Multicultural Knowledgecited by 28
  9. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learningcited by 19
  10. 2024Benchmarking Chinese Commonsense Reasoning of LLMs: From Chinese-Specifics to Reasoning-Memorization Correlationscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 13.

15 papers.

Sort:

By area:

  1. 2026Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Modelscited by 3
  2. 2025CRaFT: An Explanation-Based Framework for Evaluating Cultural Reasoning in Multilingual Language Modelscited by 2
  3. 2026SEA-Guard: Culturally Grounded Multilingual Safeguard for Southeast Asiacited by 2
  4. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  5. 2025On The Conceptualization and Societal Impact of Cross-Cultural Biascited by 1
  6. 2026Why are all LLMs Obsessed with Japanese Culture? On the Hidden Cultural and Regional Biases of LLMscited by 1
  7. 2026LoCar: Localization-Aware Evaluation of In-Vehicle Assistants through Fine-Grained Sociolinguistic Controlcited by 1
  8. 2026TARAZ: Persian Short-Answer Question Benchmark for Cultural Evaluation of Language Modelscited by 0
  9. 2026Toward Culturally Grounded Natural Language Processingcited by 0
  10. 2026HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & Adaptationcited by 0
  11. 2026C-Mining: Unsupervised Discovery of Seeds for Cultural Data Synthesis via Geometric Misalignmentcited by 0
  12. 2026MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoningcited by 0
3 more
  1. 2026CoCoA: Context-Conditional Cultural Alignment for Large Language Modelscited by 0
  2. 2026Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMscited by 0
  3. 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. 2025CURE: Cultural Understanding and Reasoning Evaluation - A Framework for "Thick" Culture Alignment Evaluation in LLMs
  2. 2026MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
  3. 2025CultureSynth: A Hierarchical Taxonomy-Guided and Retrieval-Augmented Framework for Cultural Question-Answer Synthesis
  4. 2026Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
  5. 2024Self-Pluralising Culture Alignment for Large Language Models
  6. 2026XCR-Bench: Benchmarking Cross-Cultural Reasoning in LLMs via Culture-Specific Items and Hall's Triad
  7. 2025Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
  8. 2025MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation