mlsanityData to 7 Oct 2026

M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models

arXiv 2406.16783 ↗First posted 24 Jun 2024cs.CL cs.AI cs.LGcited by 7

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

Abstract (arXiv)

Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they predominantly focus on high-resource languages like English. To better align LLMs across a broad spectrum of languages and tasks, we propose a fully synthetic, novel taxonomy (Evol) guided Multilingual, Multi-turn instruction finetuning dataset, called M2Lingual. It is constructed by first selecting a diverse set of seed examples and then utilizing the proposed Evol taxonomy to convert these seeds into complex and challenging multi-turn instructions. We demonstrate the effectiveness of M2Lingual by training LLMs of varying sizes and showcasing the enhanced performance across a diverse set of languages. We contribute the 2 step Evol taxonomy with the guided generation code: https://github.com/ServiceNow/M2Lingual, as well as the first fully synthetic, general and task-oriented, multi-turn, multilingual dataset built with Evol - M2Lingual: https://huggingface.co/datasets/ServiceNow-AI/ M2Lingual - containing 182K total IFT pairs, covering 70 languages and 17+ NLP tasks.

Key facts. Cited by 7 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 47 of its 72 references that are in the map. First posted on arXiv 24 Jun 2024.

Builds on

47 of 72 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023OpenAssistant Conversations -- Democratizing Large Language Model Alignment14 Apr
  2. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructions20 Dec

Other references · 45

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  5. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  6. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  7. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,464
  8. 2023Qwen Technical Reportcited by 3,273
  9. 2023Mistral 7Bcited by 3,065
  10. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  11. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
  12. 2024Mixtral of Expertscited by 1,785
33 more
  1. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  2. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  3. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  4. 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 913
  5. 2022Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Taskscited by 858
  6. 2023ChatGPT Outperforms Crowd-Workers for Text-Annotation Taskscited by 849
  7. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 825
  8. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 734
  9. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  10. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 598
  11. 2019On the Cross-lingual Transferability of Monolingual Representationscited by 575
  12. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  13. 2022Language Models are Multilingual Chain-of-Thought Reasonerscited by 518
  14. 2020TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languagescited by 486
  15. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 449
  16. 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
  17. 2019MLQA: Evaluating Cross-lingual Extractive Question Answeringcited by 339
  18. 2020XCOPA: A Multilingual Dataset for Causal Commonsense Reasoningcited by 330
  19. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 292
  20. 2024Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuningcited by 174
  21. 2023CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languagescited by 172
  22. 2023The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Datasetcited by 148
  23. 2023SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoningcited by 94
  24. 2023Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptationcited by 79
  25. 2024MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Modelscited by 78
  26. 2024A Closer Look at the Limitations of Instruction Tuningcited by 76
  27. 2021Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translationcited by 70
  28. 2023PolyLM: An Open Source Polyglot Large Language Modelcited by 64
  29. 2023Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpacacited by 60
  30. 2021Efficient (Soft) Q-Learning for Text Generation with Limited Good Datacited by 35
  31. 2023Empowering Cross-lingual Abilities of Instruction-tuned Large Language Models by Translation-following demonstrationscited by 34
  32. 2021Advances in Multi-turn Dialogue Comprehension: A Surveycited by 12
  33. 2023Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generationcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2025MMCR: Advancing Visual Language Model in Multimodal Multi-Turn Contextual Reasoningcited by 16
  2. 2026F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual Worldcited by 10
  3. 2024Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languagescited by 6
  4. 2025ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuningcited by 3
  5. 2025RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardwarecited by 1
  6. 2026Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challengescited by 1
  7. 2026EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
  2. 2023InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning
  3. 2024BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
  4. 2023Extrapolating Large Language Models to Non-English by Aligning Languages
  5. 2023BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
  6. 2024Enhancing and Assessing Instruction-Following with Fine-Grained Instruction Variants
  7. 2024CodecLM: Aligning Language Models with Tailored Synthetic Data
  8. 2024CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment