# RIRO: Reshaping Inputs, Refining Outputs Unlocking the Potential of Large Language Models in Data-Scarce Contexts

arXiv: https://arxiv.org/abs/2412.15254 · HTML: https://mlsanity.com/paper/2412.15254/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 40 references that are in the map.
- First posted on arXiv 15 Dec 2024.

## Builds on (most cited first, 3 of 3)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [TestART: Improving LLM-based Unit Testing via Co-evolution of Automated Generation and Repair Iteration](https://mlsanity.com/paper/2408.03095/) (2024)

## Built on by (most cited first, 6 of 6)

- [Retrieval Augmented Generation Based LLM Evaluation For Protocol State Machine Inference With Chain-of-Thought Reasoning](https://mlsanity.com/paper/2502.15727/) (2025)
- [Arabic Large Language Models for Medical Text Generation](https://mlsanity.com/paper/2509.10095/) (2025)
- [Scaling Arabic Medical Chatbots Using Synthetic Data: Enhancing Generative AI with Synthetic Patient Records](https://mlsanity.com/paper/2509.10108/) (2025)
- [A Multi-Model Metric-based Selection Framework for Abstractive Text summarization](https://mlsanity.com/paper/2606.05494/) (2026)
- [Improving Answer Extraction in Context-based Question Answering Systems Using LLMs](https://mlsanity.com/paper/2606.06197/) (2026)
- [A Self Consistency Based Reranking for Narrative Question Answering](https://mlsanity.com/paper/2606.15741/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have significantly advanced natural language processing, excelling in areas like text generation, summarization, and question-answering. Despite their capabilities, these models face challenges when fine-tuned on small, domain-specific datasets, often struggling to generalize and deliver accurate results with unfamiliar inputs. To tackle this issue, we introduce RIRO, a novel two-layer architecture designed to improve performance in data-scarce environments. The first layer leverages advanced prompt engineering to reformulate inputs, ensuring better alignment with training data, while the second layer focuses on refining outputs to minimize inconsistencies. Through fine-tuning models like Phi-2, Falcon 7B, and Falcon 1B, with Phi-2 outperforming the others. Additionally, we introduce a benchmark using evaluation metrics such as cosine similarity, Levenshtein distance, BLEU score, ROUGE-1, ROUGE-2, and ROUGE-L. While these advancements improve performance, challenges like computational demands and overfitting persist, limiting the potential of LLMs in data-scarce, high-stakes environments such as healthcare, legal documentation, and software testing.