# TULIP: Adapting Open-Source Large Language Models for Underrepresented Languages and Specialized Financial Tasks

arXiv: https://arxiv.org/abs/2508.16243 · HTML: https://mlsanity.com/paper/2508.16243/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 18 references that are in the map.
- First posted on arXiv 22 Aug 2025.

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [BloombergGPT: A Large Language Model for Finance](https://mlsanity.com/paper/2303.17564/) (2023)
- [FinGPT: Open-Source Financial Large Language Models](https://mlsanity.com/paper/2306.06031/) (2023)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance](https://mlsanity.com/paper/2306.05443/) (2023)
- [FinBen: A Holistic Financial Benchmark for Large Language Models](https://mlsanity.com/paper/2402.12659/) (2024)
- [WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain](https://mlsanity.com/paper/2211.00083/) (2022)
- [Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models](https://mlsanity.com/paper/2306.12659/) (2023)
- [Adapting Large Language Models to Domains via Reading Comprehension](https://mlsanity.com/paper/2309.09530/) (2023)
- [FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models](https://mlsanity.com/paper/2402.10986/) (2024)
- [Benchmarking Large Language Models on CFLUE -- A Chinese Financial Language Understanding Evaluation Dataset](https://mlsanity.com/paper/2405.10542/) (2024)
- [A Dutch Financial Large Language Model](https://mlsanity.com/paper/2410.12835/) (2024)
- [Optimizing Large Language Models for Turkish: New Methodologies in Corpus Selection and Training](https://mlsanity.com/paper/2412.02775/) (2024)

## Abstract (arXiv)

Thanks to the growing popularity of large language models over the years, there is great potential for their applications in finance. Despite the exceptional performance of larger proprietary models, which are presented as black-box solutions through APIs, smaller models that can be hosted on-premise present opportunities for adaptability and privacy. Especially in cases where the management of sensitive information and application of domain knowledge is important, like finance, enhancing the capabilities of smaller models becomes crucial, notably for underrepresented languages. In this work, we introduce TULIP models, which adapt Llama 3.1 8B and Qwen 2.5 7B for domain and language adaptation, focusing on financial Turkish use cases. The five-stage development pipeline involves data collection, continual pre-training (CPT), benchmark design, synthetic data generation and supervised fine-tuning (SFT). The results show that the capabilities of the models can be enhanced to effectively accomplish targeted tasks in this specific domain and language.