mlsanityData to 7 Oct 2026

LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback

arXiv 2406.01771 ↗First posted 3 Jun 2024cs.CLcited by 51

On the map: LLM alignment / RLHF / preference optimisation → LLM preference optimization methods

Abstract (arXiv)

To democratize large language models (LLMs) to most natural languages, it is imperative to make these models capable of understanding and generating texts in many languages, in particular low-resource ones. While recent multilingual LLMs demonstrate remarkable performance in such capabilities, these LLMs still support a limited number of human languages due to the lack of training data for low-resource languages. Moreover, these LLMs are not yet aligned with human preference for downstream tasks, which is crucial for the success of LLMs in English. In this paper, we introduce xLLaMA-100 and xBLOOM-100 (collectively xLLMs-100), which scale the multilingual capabilities of LLaMA and BLOOM to 100 languages. To do so, we construct two datasets: a multilingual instruction dataset including 100 languages, which represents the largest language coverage to date, and a cross-lingual human feedback dataset encompassing 30 languages. We perform multilingual instruction tuning on the constructed instruction data and further align the LLMs with human feedback using the DPO algorithm on our cross-lingual human feedback dataset. We evaluate the multilingual understanding and generating capabilities of xLLMs-100 on five multilingual benchmarks. Experimental results show that xLLMs-100 consistently outperforms its peers across the benchmarks by considerable margins, defining a new state-of-the-art multilingual LLM that supports 100 languages.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Placed in LLM preference optimization methods, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 33 of its 54 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

33 of 54 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback29 Jul
  2. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 31

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  6. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  7. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  8. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  10. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  11. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  12. 2020Language-agnostic BERT Sentence Embeddingcited by 621
19 more
  1. 2024OLMo: Accelerating the Science of Language Modelscited by 599
  2. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 575
  3. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  4. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  5. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
  6. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  7. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 292
  8. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  9. 2019PAWS-X: A Cross-lingual Adversarial Dataset for Paraphrase Identificationcited by 262
  10. 2023Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Promptingcited by 163
  11. 2020Deep Learning for Text Style Transfer: A Surveycited by 161
  12. 2023Do Multilingual Language Models Think Better in English?cited by 87
  13. 2023Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptationcited by 79
  14. 2023Extrapolating Large Language Models to Non-English by Aligning Languagescited by 69
  15. 2023Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpacacited by 60
  16. 2023Exploring the Sensitivity of LLMs' Decision-Making Capabilities: Insights from Prompt Variation and Hyperparameterscited by 32
  17. 2021Improving Both Domain Robustness and Domain Adaptability in Machine Translationcited by 11
  18. 2023Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translationcited by 5
  19. 2023Extending Multilingual Machine Translation through Imitation Learningcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 27; 2026: 13.

51 papers.

Sort:

By area:

  1. 2024M-RewardBench: Evaluating Reward Models in Multilingual Settingscited by 50
  2. 2025Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gapcited by 41
  3. 2025A Survey of Direct Preference Optimizationcited by 35
  4. 2024In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translationcited by 21
  5. 2024Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Modelscited by 20
  6. 2025ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilingualitycited by 19
  7. 2024EMMA-500: Enhancing Massively Multilingual Adaptation of Large Language Modelscited by 16
  8. 2025Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translationcited by 13
  9. 2024Multi-OphthaLingua: A Multilingual Benchmark for Assessing and Debiasing LLM Ophthalmological QA in LMICscited by 10
  10. 2025Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignmentcited by 10
  11. 2025TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarkingcited by 9
  12. 2024Evaluating Cultural Awareness of LLMs for Yoruba, Malayalam, and Englishcited by 8
38 more
  1. 2025Joint Localization and Activation Editing for Low-Resource Fine-Tuningcited by 7
  2. 2025Redefining Machine Translation on Social Network Services with Large Language Modelscited by 6
  3. 2025From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corporacited by 6
  4. 2025Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challengescited by 6
  5. 2024Lens: Rethinking Multilingual Enhancement for Large Language Modelscited by 5
  6. 2024One world, one opinion? The superstar effect in LLM responsescited by 5
  7. 2025DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detectioncited by 5
  8. 2025Is Small Language Model the Silver Bullet to Low-Resource Languages Machine Translation?cited by 5
  9. 2025Document Intelligence in the Era of Large Language Models: A Surveycited by 5
  10. 2025Do Large Language Models Truly Understand Cross-cultural Differences?cited by 5
  11. 2024KAHANI: Culturally-Nuanced Visual Storytelling Tool for Non-Western Culturescited by 4
  12. 2025Massively Multilingual Adaptation of Large Language Models Using Bilingual Translation Datacited by 4
  13. 2025Aligning Large Language Models to Low-Resource Languages through LLM-Based Selective Translation: A Systematic Studycited by 4
  14. 2025Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a surveycited by 4
  15. 2026TurkBench: A Benchmark for Evaluating Turkish Large Language Modelscited by 4
  16. 2026Cross-Lingual Activation Steering for Multilingual Language Modelscited by 4
  17. 2025Text2Cypher Across Languages: Evaluating and Finetuning LLMscited by 3
  18. 2025Llama-GENBA-10B: A Trilingual Large Language Model for German, English and Bavariancited by 3
  19. 2024Chain-of-MetaWriting: Linguistic and Textual Analysis of How Small Language Models Write Young Students Textscited by 2
  20. 2024sPhinX: Sample Efficient Multilingual Instruction Fine-Tuning Through N-shot Guided Promptingcited by 1
  21. 2025TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translationcited by 1
  22. 2025Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Modelscited by 1
  23. 2026Is MT Ready for the Next Crisis or Pandemic?cited by 1
  24. 2026The GaoYao Benchmark: A Comprehensive Framework for Evaluating Multilingual and Multicultural Abilities of Large Language Modelscited by 1
  25. 2026MADE: Beyond Scoring via a Multilingual Agentic Diagnosing Engine for Fine-Grained Evaluation Insightscited by 1
  26. 2025Can MLLMs Generalize to Multi-Party dialog? Exploring Multilingual Response Generation in Complex Scenarioscited by 0
  27. 2025MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesiscited by 0
  28. 2025Elite Polarization in European Parliamentary Speeches: a Novel Measurement Approach Using Large Language Modelscited by 0
  29. 2025MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMscited by 0
  30. 2025M-DaQ: Retrieving Samples with Multilingual Diversity and Quality for Instruction Fine-Tuning Datasetscited by 0
  31. 2025Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretrainingcited by 0
  32. 2026Incremental Multilingual Text2Cypher with Adapter Combinationcited by 0
  33. 2026Towards AI Evaluation in Domain-Specific RAG Systems: The AgriHubi Case Studycited by 0
  34. 2026Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Designcited by 0
  35. 2026Mimir: Large-scale Multilingual Concept Modelingcited by 0
  36. 2026Meta-Learning Preferences for Multilingual LLM Alignmentcited by 0
  37. 2026Language Chain in Alignment: Cross-lingual Ranking Preference Optimizationcited by 0
  38. 2026M-SQE: Multilingual Skill Quality Estimation for Enhancing Language Equality in Agentic Skill Usecited by 0

50 most cited of 51 All 51 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages
  2. 2026English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training
  3. 2026EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training
  4. 2024Teaching LLMs to Abstain across Languages via Multilingual Feedback
  5. 2023TencentLLMEval: A Hierarchical Evaluation of Real-World Capabilities for Human-Aligned LLMs
  6. 2025MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation
  7. 2024Multilingual Large Language Models: A Systematic Survey
  8. 2024SambaLingo: Teaching Large Language Models New Languages