arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01788cs.CLcs.AIcs.IR
收藏

LitLLM:一个用于科学文献综述的工具包

LitLLM: A Toolkit for Scientific Literature Review

ServiceNow Research(ServiceNow研究院);Mila - Quebec AI Institute(米拉-魁北克人工智能研究所);HEC Montreal(蒙特利尔高等商学院);University of Waterloo(滑铁卢大学)

Shubham Agarwal, Gaurav Sahu, Abhay Puri, Issam H. Laradji, Krishnamurthy DJ Dvijotham, Jason Stanley, Laurent Charlin, Christopher Pal

AI总结:

针对现有大语言模型生成文献综述存在幻觉、遗漏最新研究的问题,提出基于RAG原理、结合专门提示技术的LitLLM工具包,经检索、重排序后生成综述,大幅提升效率。

摘要:

为科研论文撰写文献综述对于理解研究内容、其局限性以及在现有工作基础上开展研究至关重要。这是一项繁琐的任务,因此自动文献综述生成器颇具吸引力。遗憾的是,现有许多利用大语言模型(Large Language Models, LLMs)生成此类综述的工作存在显著局限性:它们容易产生幻觉——生成非事实性信息——并且会忽略其训练数据未覆盖的最新研究。为解决这些局限,我们提出一个基于检索增强生成(Retrieval Augmented Generation, RAG)原理、借助LLMs采用专门提示与指令技术的工具包。我们的系统首先启动网络搜索,通过现成的LLM将用户提供的摘要总结为关键词,以此检索相关论文。作者可补充相关论文或关键词来优化搜索,实现定制化的检索流程。其次,系统根据用户提供的摘要对检索到的论文进行重排序。最后,基于重排序结果和摘要生成相关工作部分。与传统方法相比,文献综述的时间和工作量大幅减少,证明我们的工具包是一种高效的替代方案。包含演示和工具包的项目页面可通过以下链接访问:https://litllm.github.io

英文摘要:

Conducting literature reviews for scientific papers is essential for understanding research, its limitations, and building on existing work. It is a tedious task which makes an automatic literature review generator appealing. Unfortunately, many existing works that generate such reviews using Large Language Models (LLMs) have significant limitations. They tend to hallucinate-generate non-factual information-and ignore the latest research they have not been trained on. To address these limitations, we propose a toolkit that operates on Retrieval Augmented Generation (RAG) principles, specialized prompting and instructing techniques with the help of LLMs. Our system first initiates a web search to retrieve relevant papers by summarizing user-provided abstracts into keywords using an off-the-shelf LLM. Authors can enhance the search by supplementing it with relevant papers or keywords, contributing to a tailored retrieval process. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Finally, the related work section is generated based on the re-ranked results and the abstract. There is a substantial reduction in time and effort for literature review compared to traditional methods, establishing our toolkit as an efficient alternative. Our project page including the demo and toolkit can be accessed here: https://litllm.github.io

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。

↑