mlsanityData to 14 Oct 2026

TIBSTC-CoT: A Multi-Domain Instruction Dataset for Chain-of-Thought Reasoning in Language Models

arXiv 2508.01977 ↗First posted 4 Aug 2025cs.CL cs.AIcited by 3

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

To address the severe data scarcity in Tibetan, a low-resource language spoken by over six million people, we introduce TIBSTC-CoT, the large-scale, multi-domain Tibetan dataset automatically constructed via chain-of-thought prompting with large language models (LLMs). TIBSTC-CoT establishes a scalable and reproducible framework for dataset creation in low-resource settings, covering diverse domains and reasoning patterns essential for language understanding and generation. Building on this dataset, we develop the Sunshine-thinking LLM family, a series of Tibetan-centric LLMs equipped with chain-of-thought capabilities. Trained entirely on TIBSTC-CoT, Sunshine-thinking has demonstrated strong reasoning and generation performance, comparable to state-of-the-art (SOTA) multilingual LLMs. Our work marks a significant step toward inclusive AI by enabling high-quality Tibetan language processing through both resource creation and model innovation. All data are available: https://github.com/Vicentvankor/sun-shine.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 33 of its 52 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

33 of 52 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023LaRS: Latent Reasoning Skills for Chain-of-Thought Reasoning7 Dec
  2. 2022Large Language Models are Zero-Shot Reasoners24 May
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 29

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2025Qwen3 Technical Reportcited by 8,820
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  7. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  8. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  9. 2022Scaling Instruction-Finetuned Language Modelscited by 3,024
  10. 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
  11. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  12. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,121
17 more
  1. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
  2. 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 742
  3. 2023The Flan Collection: Designing Data and Methods for Effective Instruction Tuningcited by 739
  4. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  5. 2023Textbooks Are All You Needcited by 569
  6. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  7. 2023Efficient and Effective Text Encoding for Chinese LLaMA and Alpacacited by 305
  8. 2024Quiet-STaR: Language Models Can Teach Themselves to Think Before Speakingcited by 301
  9. 2021Few-shot Learning with Multilingual Language Modelscited by 278
  10. 2023HuaTuo: Tuning LLaMA Model with Chinese Medical Knowledgecited by 162
  11. 2024mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Modelscited by 33
  12. 2025Demystifying Multilingual Chain-of-Thought in Process Reward Modelingcited by 6
  13. 2025TLUE: A Tibetan Language Understanding Evaluation Benchmarkcited by 6
  14. 2025From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetancited by 4
  15. 2025TFD: A Comprehensive Structured Tibetan Foundation Dataset for Low-Resource Language Processing and Large-Scale Modelingcited by 3
  16. 2025FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for "U-Tsang, Amdo and Kham Speech Dataset Generationcited by 3
  17. 2025TiSpell: A Semi-Masked Methodology for Tibetan Spelling Correction covering Multi-Level Error with Data Augmentationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2025Tibetan Language and AI: A Comprehensive Survey of Resources, Methods and Challengescited by 1
  2. 2026Tibetan-TTS:Low-Resource Tibetan Speech Synthesis with Large Model Adaptationcited by 0
  3. 2026Nigeria Machinery: A Low-Resource Industrial Dataset with a Domain-Grounded Reasoning Layercited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning Transfer for an Extremely Low-Resource and Endangered Language: Bridging Languages Through Sample-Efficient Language Understanding
  2. 2025Reasoning Beyond Limits: Advances and Open Problems for LLMs
  3. 2025LaoBench: A Large-Scale Multidimensional Lao Benchmark for Large Language Models
  4. 2025Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging -- An Open Recipe
  5. 2025CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
  6. 2024ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting
  7. 2025Long Chain-of-Thought Reasoning Across Languages
  8. 2024SUTRA: Scalable Multilingual Language Model Architecture