arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节（Veterans Day），12 日无更新
arXiv 2402.01722cs.CLcs.AI
收藏

提升大型语言模型性能以更准确地回答问题与提取信息

Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately

Liang Zhang, Katherine Jijo, Spurthi Setty, Eden Chung, Fatima Javid, Natan Vidra, Tommy Clifford

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究通过微调大型语言模型并结合检索增强生成，在金融数据集上显著提升了问答与信息提取的准确性。

摘要：

大型语言模型（LLMs）能够生成对问题的回答；然而，其有效性常常受到回答质量欠佳以及偶尔无法提供准确回答的阻碍。为应对这些挑战，本文采用了一种微调过程，通过反馈和示例来优化模型。其目标是通过持续反馈循环增强AI模型，并利用余弦相似度、LLM评估和Rouge-L分数等指标来评估模型。借助GPT-3.5、GPT4ALL、LLaMA2和Claude等LLM，该方法在金融数据集（包括FinanceBench和RAG Instruct Benchmark Tester Dataset）上进行了基准测试，说明了微调的必要性。结果表明，微调后的模型能够超越零样本LLM的准确性，提供更优的问答能力。值得注意的是，将LLM微调与一种称为检索增强生成（RAG）的过程相结合，被证明能够生成具有更高准确性的响应。

英文摘要：

Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models. The objective is to enhance AI models through continuous feedback loops, utilizing metrics such as cosine similarity, LLM evaluation and Rouge-L scores to evaluate the models. Leveraging LLMs like GPT-3.5, GPT4ALL, and LLaMA2, and Claude, this approach is benchmarked on financial datasets, including the FinanceBench and RAG Instruct Benchmark Tester Dataset, illustrating the necessity of fine-tuning. The results showcase the capability of fine-tuned models to surpass the accuracy of zero-shot LLMs, providing superior question and answering capabilities. Notably, the combination of fine-tuning the LLM with a process known as Retrieval Augmented Generation (RAG) proves to generate responses with improved accuracy.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑