通过分类QA对提升大模型事实嵌入效果，发现概念类数据更优。
Beyond QA Pairs: Assessing Parameter-Efficient Fine-Tuning for Fact Embedding in LLMs
- 用BERT分类器将QA对分为事实型与概念型，指导微调策略。
- 概念型数据训练的模型在推荐任务中显著优于事实型数据。
- 合成数据生成方法D-Naive比D-RAG更有效，适合特定领域优化。
本文系统评估了参数高效微调（PEFT）在将领域特定事实嵌入大语言模型（LLMs）中的效果。通过基于BERT的分类器，将问题-答案对划分为事实型和概念型，并分别用于微调两个Llama-2模型。使用GPT-3.5 Turbo和Gemini进行评估，结果表明：概念型数据训练的模型表现更优。此外，对比两种合成数据生成方法D-RAG与D-Naive，D-Naive表现更佳。尽管PEFT在指令任务中表现出色，但在事实嵌入方面并非最优。在数据中心领域的1000样本数据集上，微调后的Llama-2 7B模型在生成产品推荐方面显著优于基线模型。研究强调了QA分类与合成数据生成技术对提升模型性能的关键作用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。