# Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLMs

arXiv: https://arxiv.org/abs/2503.01131 · HTML: https://mlsanity.com/paper/2503.01131/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 12 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 12 of 12)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning](https://mlsanity.com/paper/2308.12032/) (2023)
- [ToolQA: A Dataset for LLM Question Answering with External Tools](https://mlsanity.com/paper/2306.13304/) (2023)
- [RAFT: Adapting Language Model to Domain Specific RAG](https://mlsanity.com/paper/2403.10131/) (2024)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [MoDS: Model-oriented Data Selection for Instruction Tuning](https://mlsanity.com/paper/2311.15653/) (2023)
- [RAG vs Fine-tuning: Pipelines, Tradeoffs, and a Case Study on Agriculture](https://mlsanity.com/paper/2401.08406/) (2024)
- [Rethinking Data Selection for Supervised Fine-Tuning](https://mlsanity.com/paper/2402.06094/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learning a Canonical Basis of Human Preferences from Binary Ratings](https://mlsanity.com/paper/2503.24150/) (2025)

## Abstract (arXiv)

This paper presents an extensive examination of Parameter-Efficient Fine-Tuning (PEFT) for embedding domain specific facts into Large Language Models (LLMs), focusing on improving the fine-tuning process by categorizing question-answer (QA) pairs into Factual and Conceptual classes using a BERT-based classifier. Two distinct Llama-2 models are fine-tuned based on these classifications and evaluated using larger models like GPT-3.5 Turbo and Gemini. Our results indicate that models trained on conceptual datasets outperform those trained on factual datasets. Additionally, we compare the efficiency of two synthetic fine-tuning dataset generation techniques, D-RAG and D-Naive, with D-Naive demonstrating superior performance. Although PEFT has shown effectiveness, our research indicates that it may not be the most optimal method for embedding facts into LLMs. However, it has demonstrated exceptional performance in instruction-based tasks. Our findings are reinforced by a 1000-sample dataset in the data center domain, where the fine-tuned Llama-2 7B model significantly outperforms the baseline model in generating product recommendations. Our study highlights the importance of QA pair categorization and synthetic dataset generation techniques in enhancing the performance of LLMs in specific domains.