# Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks

arXiv: https://arxiv.org/abs/2503.13988 · HTML: https://mlsanity.com/paper/2503.13988/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Generated Knowledge Prompting for Commonsense Reasoning](https://mlsanity.com/paper/2110.08387/) (2021)
- [LLM in a flash: Efficient Large Language Model Inference with Limited Memory](https://mlsanity.com/paper/2312.11514/) (2023)
- [BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages](https://mlsanity.com/paper/2406.09948/) (2024)
- [From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language Representation](https://mlsanity.com/paper/2404.09138/) (2024)
- [Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains](https://mlsanity.com/paper/2411.14647/) (2024)
- [ZNO-Eval: Benchmarking reasoning capabilities of large language models in Ukrainian](https://mlsanity.com/paper/2501.06715/) (2025)

## Built on by (most cited first, 2 of 2)

- [Prompting Strategies for Language Model-Based Item Generation in K-12 Education: Bridging the Gap Between Small and Large Language Models](https://mlsanity.com/paper/2508.20217/) (2025)
- [SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses](https://mlsanity.com/paper/2607.02049/) (2026)

## Abstract (arXiv)

Leading large language models have demonstrated impressive capabilities in reasoning-intensive tasks, such as standardized educational testing. However, they often require extensive training in low-resource settings with inaccessible infrastructure. Small or compact models, though more efficient, frequently lack sufficient support for underrepresented languages, leaving a performance gap in critical domains. This work explores the potential of parameter-efficient fine-tuning of compact open-weight language models to handle reasoning-intensive tasks in the underrepresented Ukrainian language, building on the findings of the ZNO-Eval benchmark. Parameter-efficient fine-tuning of LLaMA 3.1 (8 billion parameters), LLaMA 3.2 (3 billion parameters), and Gemma 2 (9 billion parameters) models on chain-of-thought solutions resulted in a modest test score improvement of up to 17.4% on complex matching tasks and 1.6% overall compared to tuning on answer letters alone, offering enhanced interpretability and robustness. In addition, the proposed tuning method with joint task topic and step-by-step solution generation outperforms standard chain-of-thought tuning in matching tasks and provides a 5.4% gain over the best LLaMA 3.2 model due to guiding the model to recall and apply domain-relevant information. Contrasting obtained results with zero-shot evaluations of leading open-weight and proprietary models such as Qwen, DeepSeek R1, OpenAI o1 and o3, Gemini, and Claude, highlight that fine-tuning LLaMA and Gemma models with 2,032 step-by-step solutions and 20 to 50 million trainable parameters on a single A100 GPU lets them outperform GPT-4o mini, Mistral Large, and larger open-weight models. This research also evaluates how merging the quantized adapter with the base model influences the generation quality. Source code and tuned models are available at https://github.com/NLPForUA/ZNO.