mlsanityData to 7 Oct 2026

X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions

arXiv 2405.19744 ↗First posted 30 May 2024cs.CL cs.AIcited by 18

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

Abstract (arXiv)

Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English samples into these languages can be a solution but unreliable, leading to responses with translation errors and lacking language-specific or cultural knowledge. To address this issue, we propose a novel method to construct cross-lingual instruction following samples with instruction in English and response in low-resource languages. Specifically, the language model first learns to generate appropriate English instructions according to the natural web texts in other languages as responses. The candidate cross-lingual instruction tuning samples are further refined and diversified. We have employed this method to build a large-scale cross-lingual instruction tuning dataset on 10 languages, namely X-Instruction. The instruction data built using our method incorporate more language-specific knowledge compared with the naive translation method. Experimental results have shown that the response quality of the model tuned on X-Instruction greatly exceeds the model distilled from a powerful teacher model, reaching or even surpassing the ones of ChatGPT. In addition, we find that models tuned on cross-lingual instruction following samples can follow the instruction in the output language without further tuning.

Key facts. Cited by 18 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 28 of its 42 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

28 of 42 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision4 May
  2. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignment14 Apr
  3. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructions20 Dec
  4. 2022Training language models to follow instructions with human feedback4 Mar

Other references · 24

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  5. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  6. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 2,950
  7. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,205
  9. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  10. 2017Mixed Precision Trainingcited by 1,135
  11. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  12. 2020MPNet: Masked and Permuted Pre-training for Language Understandingcited by 973
12 more
  1. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 913
  2. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 696
  3. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  4. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  5. 2023Low-Resource Languages Jailbreak GPT-4cited by 290
  6. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  7. 2018Constituency Parsing with a Self-Attentive Encodercited by 196
  8. 2023CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languagescited by 172
  9. 2018Multilingual Constituency Parsing with Self-Attention and Pre-Trainingcited by 117
  10. 2023Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptationcited by 79
  11. 2023BUFFET: Benchmarking Large Language Models for Few-shot Cross-lingual Transfercited by 68
  12. 2023Explore-Instruct: Enhancing Domain-Specific Instruction Coverage through Active Explorationcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 11; 2026: 5.

18 papers.

Sort:

By area:

  1. 2024Unlocking the Potential of Model Merging for Low-Resource Languagescited by 19
  2. 2025Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basquecited by 12
  3. 2025Enhancing Non-English Capabilities of English-Centric Large Language Models through Deep Supervision Fine-Tuningcited by 11
  4. 2025XIFBench: Evaluating Large Language Models on Multilingual Instruction Followingcited by 11
  5. 20241+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators?cited by 9
  6. 2025Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignmentcited by 9
  7. 2025Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in Kazakhcited by 4
  8. 2025Aligning Large Language Models to Low-Resource Languages through LLM-Based Selective Translation: A Systematic Studycited by 4
  9. 2026Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMscited by 3
  10. 2025A Survey of Large Language Models in Discipline-specific Research: Challenges, Methods and Opportunitiescited by 2
  11. 2025XL-Suite: Cross-Lingual Synthetic Training and Evaluation Data for Open-Ended Generationcited by 1
  12. 2025GemMaroc: Unlocking Darija Proficiency in LLMs with Minimal Datacited by 1
6 more
  1. 2025LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgishcited by 1
  2. 2025CUTE: A Multilingual Dataset for Enhancing Cross-Lingual Knowledge Transfer in Low-Resource Languagescited by 0
  3. 2026Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgishcited by 0
  4. 2026LLMs Get Smarter from Targeted Synthetic Multilingual Datacited by 0
  5. 2026EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languagescited by 0
  6. 2026PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibrationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024xCoT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning
  2. 2024CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment
  3. 2023InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning
  4. 2023Extrapolating Large Language Models to Non-English by Aligning Languages
  5. 2025Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
  6. 2024LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Reasoning
  7. 2024LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback
  8. 2024Pipeline Analysis for Developing Instruct LLMs in Low-Resource Languages: A Case Study on Basque