Scholarlink

<p>Recent advancements in large language models (LLMs) have demonstrated their effectiveness across various natural language processing tasks, including question answering. However, adapting these models to domain-specific applications, such as academic question answering (Academic QA), presents challenges, particularly when computational resources are limited. This paper explores the use of parameter-efficient fine-tuning techniques, specifically Low-Rank Adaptation (LoRA), to optimize open-source LLMs for academic QA tasks. We fine-tune LLaMA-7B and Bloomz models on a subset of The Pile dataset, focusing on academic and technical content. Our results show that LoRA-based fine-tuning improves model performance on academic QA tasks, even in resource-constrained settings, providing valuable insights into the applicability of these models in educational contexts.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

AcaQAS: An Academic Question Answering System Based on Finetuning Large Language Models

  • 期刊论文

  • 发表日期：

    2025年7月26日

查看全文
  • Thai Hoang Le,
  • Bao Thai Duong

摘要

Recent advancements in large language models (LLMs) have demonstrated their effectiveness across various natural language processing tasks, including question answering. However, adapting these models to domain-specific applications, such as academic question answering (Academic QA), presents challenges, particularly when computational resources are limited. This paper explores the use of parameter-efficient fine-tuning techniques, specifically Low-Rank Adaptation (LoRA), to optimize open-source LLMs for academic QA tasks. We fine-tune LLaMA-7B and Bloomz models on a subset of The Pile dataset, focusing on academic and technical content. Our results show that LoRA-based fine-tuning improves model performance on academic QA tasks, even in resource-constrained settings, providing valuable insights into the applicability of these models in educational contexts.