mlsanityData to 14 Oct 2026

Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency

arXiv 2605.22137 ↗First posted 21 May 2026cs.CLcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across languages. While prompting LLMs in English typically yields the highest general performance, it often induces a Western-centric bias, hindering the model's ability to accurately reflect diverse cultural knowledge. We hypothesize that LLMs already possess rich cultural knowledge embedded within local-language representations, but fail to retrieve it when prompted in English. To bridge this cross-lingual knowledge gap, we propose a novel self-supervised framework. Our method leverages multilingual self-consistency to identify the most reliable cultural responses across languages, combined with a self-critique mechanism to transfer this knowledge to the weaker language. Evaluations on the BLEnD benchmark demonstrate that our approach significantly improves cultural alignment-boosting performance on English queries by an average of 5.03%-relying entirely on self-generated data. Ultimately, our work demonstrates that latent cultural knowledge can be successfully surfaced and propagated across languages, enabling more culturally equitable and consistent LLMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 9 of its 35 references that are in the map. First posted on arXiv 21 May 2026.

Builds on

9 of 35 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Beyond Accuracy: Evaluating the Reasoning Behavior of Large Language Models -- A Survey2 Apr

Other references · 8

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  4. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  5. 2024Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual Evaluationcited by 191
  6. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 173
  7. 2024Massively Multi-Cultural Knowledge Acquisition & LM Benchmarkingcited by 63
  8. 2023Large Language Models as Superpositions of Cultural Perspectivescited by 49

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Rethinking Cross-lingual Alignment: Balancing Transfer and Cultural Erasure in Multilingual LLMs
  2. 2025CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering
  3. 2024Self-Alignment: Improving Alignment of Cultural Values in LLMs via In-Context Learning
  4. 2025Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
  5. 2024Self-Pluralising Culture Alignment for Large Language Models
  6. 2026MSQA: A Natively Sourced Multilingual and Multicultural SimpleQA Benchmark
  7. 2026Aligned but Flattened: Analyzing the Trade-off between Cultural Alignment and Diversity in LLMs
  8. 2025CulFiT: A Fine-grained Cultural-aware LLM Training Paradigm via Multilingual Critique Data Synthesis