mlsanityData to 7 Oct 2026

Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models

arXiv 2512.14926 ↗First posted 16 Dec 2025cs.CL cs.AI cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning

Abstract (arXiv)

Focusing on low-resource languages is an essential step toward democratizing generative AI. In this work, we contribute to reducing the multimodal NLP resource gap for Romanian. We translate the widely known Flickr30K dataset into Romanian and further extend it for visual question answering by leveraging open-source LLMs. We demonstrate the usefulness of our datasets by fine-tuning open-source VLMs on Romanian visual question answering. We select VLMs from three widely used model families: LLaMA 3.2, LLaVA 1.6, and Qwen2. For fine-tuning, we employ the parameter-efficient LoRA method. Our models show improved Romanian capabilities in visual QA, as well as on tasks they were not trained on, such as Romanian image description generation. The seven-billion-parameter Qwen2-VL-RoVQA obtains top scores on both tasks, with improvements of +2.29% and +4.45% in BERTScore F1 on VQA and captioning, respectively, over its original version. Finally, the models show substantial reductions in grammatical errors compared to their original forms, indicating improvements not only in language understanding but also in Romanian fluency.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 21 of its 33 references that are in the map. First posted on arXiv 16 Dec 2025.

Builds on

21 of 33 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Maya: An Instruction Finetuned Multilingual Multimodal Model10 Dec
  2. 2024Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models25 Jun

Other references · 19

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  5. 2023Visual Instruction Tuningcited by 7,792
  6. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  7. 2023Improved Baselines with Visual Instruction Tuningcited by 4,362
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  9. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  10. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  11. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  12. 2018Object Hallucination in Image Captioningcited by 661
7 more
  1. 2023G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Modelcited by 208
  2. 2023Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videoscited by 84
  3. 2024PALO: A Polyglot Large Multimodal Model for 5B Peoplecited by 34
  4. 2024X-LLaVA: Optimizing Bilingual Large Vision-Language Alignmentcited by 10
  5. 2025Chitrarth: Bridging Vision and Language for a Billion Peoplecited by 10
  6. 2024LaVy: Vietnamese Multimodal Large Language Modelcited by 5
  7. 2025Evaluating Open-Source Vision-Language Models for Multimodal Sarcasm Detectioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs
  2. 2024Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Directions
  3. 2024VLR-Bench: Multilingual Benchmark Dataset for Vision-Language Retrieval Augmented Generation
  4. 2023InfMLLM: A Unified Framework for Visual-Language Tasks
  5. 2023LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models
  6. 2024Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
  7. 2024Visual Question Answering Instruction: Unlocking Multimodal Large Language Model To Domain-Specific Visual Multitasks
  8. 2024Towards Flexible Evaluation for Generative Visual Question Answering