mlsanityData to 14 Oct 2026

Building Large-Scale English-Romanian Literary Translation Resources with Open Models

arXiv 2509.07829 ↗First posted 9 Sep 2025cs.CL cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Literary translation has recently gained attention as a distinct and complex task in machine translation research, yet translation by small open models remains an open problem, particularly for low-resource languages such as Romanian. We introduce the TinyFabulist Translation Framework (TF2), a unified framework for dataset creation, fine-tuning, and evaluation in English → Romanian literary translation. Building on DS-TF1-EN-3M, the largest collection of synthetic English fables to date, our pipeline first generates 15k high-quality Romanian references from the TF1 pool using a high-performing large language model (LLM). We then apply a two-stage fine-tuning process to a 12B-parameter open-weight model: (i) instruction tuning to capture genre-specific narrative style, and (ii) adapter compression for efficient deployment. Evaluation combines a five-dimension LLM-based rubric (accuracy, fluency, coherence, style, cultural adaptation) as the primary comparative framework, alongside corpus-level Bilingual Evaluation Understudy (BLEU) reported as a secondary reference-based consistency metric. Our fine-tuned model (TF2-12B) achieves strong fluency and adequacy, narrowing the gap to top-performing proprietary models under automated and human-anchored evaluation, while being open, accessible, and significantly more cost-effective. We publicly release the fine-tuned model and two large-scale synthetic parallel datasets (DS-TF2-EN-RO-3M and DS-TF2-EN-RO-15K), along with all scripts and evaluation prompts. TF2 provides an end-to-end, reproducible pipeline for research on cost-efficient translation, cross-lingual narrative generation, and the broad adoption of open models for culturally significant literary content in low-resource settings.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 9 Sep 2025.

Builds on

29 of 48 references.

References · 29

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  4. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  5. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  6. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,919
  7. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
  8. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  10. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  11. 2024DeepSeek LLM: Scaling Open-Source Language Models with Longtermismcited by 642
  12. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 449
17 more
  1. 2023Large Language Models Are State-of-the-Art Evaluators of Translation Qualitycited by 420
  2. 2024On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Surveycited by 244
  3. 2023Large language models effectively leverage document-level context for literary translation, but critical errors persistcited by 80
  4. 2018BLEU is Not Suitable for the Evaluation of Text Simplificationcited by 78
  5. 2024A Survey on LoRA of Large Language Modelscited by 67
  6. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Codecited by 61
  7. 2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
  8. 2024Reasoning in Token Economies: Budget-Aware Evaluation of LLM Reasoning Strategiescited by 45
  9. 2023Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Modelscited by 28
  10. 2023Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMscited by 25
  11. 2024How Good Are LLMs for Literary Translation, Really? Literary Translation Evaluation with Humans and LLMscited by 23
  12. 2025EuroLLM-9B: Technical Reportcited by 17
  13. 2022A Corpus for Understanding and Generating Moral Storiescited by 16
  14. 2024LoRA-C: Parameter-Efficient Fine-Tuning of Robust CNN for IoT Devicescited by 10
  15. 2025LiTransProQA: an LLM-based Literary Translation evaluation metric with Professional Question Answeringcited by 10
  16. 2025MAATS: A Multi-Agent Automated Translation System Based on MQM Evaluationcited by 5
  17. 2025TF1-EN-3M: Three Million Synthetic Moral Fables for Training Small, Open Language Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compressioncited by 1
  2. 2026FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inferencecited by 0