值得信赖的科研摘要
我们由生成式 AI 驱动的试点搜索模型可帮助您查找科研论文,并在数秒内将数十年的研究成果提炼成清晰易懂的摘要。
值得一提的是,我们的先进工程限制了产生“幻觉”(即人工智能生成的虚假信息)的风险,并且利用了世界上最大的科学文献数据库中收录的值得信赖且经过验证的知识。
非常抱歉,我们不完全支持您的浏览器。如果您可以选择,请升级到较新版本或使用 Mozilla Firefox、Microsoft Edge、Google Chrome 或 Safari 14 或更高版本。如果您无法进行此操作且需要支持,请将您的反馈发送给我们。
全新设计的官网为您带来全新体验,期待您的反馈(在新的选项卡/窗口中打开)
Elsevier 的全新生成式 AI 能够为您提供简洁、可靠且基于人工智能的查询摘要。
无论您是想快速掌握新领域的知识,还是想找到跨学科的合作伙伴来将自己的科研推向新的高度,Scopus AI 都能助您一臂之力。
我们由生成式 AI 驱动的试点搜索模型可帮助您查找科研论文,并在数秒内将数十年的研究成果提炼成清晰易懂的摘要。
值得一提的是,我们的先进工程限制了产生“幻觉”(即人工智能生成的虚假信息)的风险,并且利用了世界上最大的科学文献数据库中收录的值得信赖且经过验证的知识。
1. 输入您的自然语言查询开始搜索 2. 查看为您生成的结果摘要,包括提高透明度和信任度的 Scopus 参考资料 3. 深入进行相关查询并发现新视角 4. 即将推出: 通过图谱查看关键词之间的联系
除了扩展摘要之外,Scopus AI 还会提出“深入”的问题,选择其中一个问题会引发新的问题,帮助您深入研究并拓宽理解。
有兴趣听取该领域最具影响力的声音吗?基础论文选项列出了涉及任何主题的最具影响力的 Scopus 论文,引导您了解一门学科的基础知识。
Scopus AI 还使用文摘中的关键词为每次查询生成概念图。正如这段短视频所解释的那样,概念图提供了主题空间的全面鸟瞰图,帮助您更完整地了解您的主题及其与其他科研领域的关系,甚至是那些超出您不熟悉的领域。
主题专家功能利用 Scopus 中 1960 多万综合作者个人资料,查找与您的查询相关的顶尖科研人员,并生成他们的工作和贡献摘要。
鉴于透明度是我们重要的 GenAI 开发原则之一,我们会说明选择每位人员的理由。
在科研和教育中使用生成式人工智能会带来安性全、准确性和道德方面的关键问题(在新的选项卡/窗口中打开),必须得到深思熟虑的指导,如联合国教科文组织 2023 年发布的这份报告(在新的选项卡/窗口中打开)。Scopus AI 的构建和维护旨在提供高等教育和科研组织所需洞察的透明度、安全性、准确性和相关性。
十多年来,Elsevier 一直在我们的产品中负责任地使用人工智能和机器学习技术,并结合我们无与伦比的同行评审内容、广泛的数据集和复杂的分析。Scopus AI 的开发遵循Elsevier 的五大负责任人工智能原则。与其他工具的不同之处在于:
显示对摘要中使用的文档文摘的清晰且可验证的参考
有法律和技术保护,确保没有数据交换或使用 Elsevier 数据来培训 OpenAI 的公共模型
遵守欧洲《通用数据保护条例》(GDPR),保证用户隐私并避免不必要的数据保留
The technology that underpins Scopus AI is maintained for:
Transparency: Only trusted Scopus content is used in Scopus AI responses and any claims or assumptions are backed up by references. Scopus AI also indicates how confident it is that its response matches your query. And if it can’t find relevant results, it tells you.
Reliability: Scopus AI features our patent-pending RAG fusion technology, which improves the quality of both the search and responses. The LLM is also guided by strict prompt engineering guardrails.
自设计阶段以来,科研界一直在贡献想法和反馈,全球数千名科研人员参与了严格的 Scopus AI 先前版本测试。我们参与的用户社区继续影响 Scopus AI 的发展,许多用户驱动的改善正在推进中。通过听取用户反馈,我们知道已经开发出了一种满足学术界需求和用例的工具。
与 Elsevier 的代表讨论您的科研需求。
在本页面上,我们介绍了一些社区最常见的问题。
Scopus AI 是集成在 Scopus 网站上的一款生成式人工智能增强型科研工具,可帮助不同学科的初级学者和科研人员浏览和理解学术内容。该工具可帮助用户理解不熟悉的学术领域、促进探索并提供基于 Scopus 作品和文摘的摘要视图,很快还将提供基于相关关键词的可视化图谱显示,帮助用户获得更宽广的视角。
Scopus AI 测试目前使用最新的大型语言模型 (LLM) 和其他技术,同时结合 Elsevier 自身的技术
在本次试点初期,我们使用了 2018 年至今的所有 Scopus 内容类型(元数据和文摘;但不包括全文文章)
我们使用的是私有 LLM,即没有通过数据交换或使用我们的数据来训练公共模型——这一重要特性的实施为数据出版商和作者提供了隐私保障,让他们彻底放心
Scopus AI 在对您的查询生成回复时,会使用自 2013 年以来发布的以下内容类型的元数据和文摘(会议评审、勘误表和撤回项目除外):
文章
书籍
书籍章节
评审
简短调查
数据论文
我们选择 2013 年作为开始年份,以确保您收到的回复是基于最近的内容。对于该工具提供的基础论文列表,Scopus AI 会挖掘整个 Scopus 语料库,为您提供关于所选主题的有影响力文章的全面列表。
关于生成式人工智能的注意事项
虽然 Scopus AI 努力将其摘要和生成式人工智能特性建立在可信的 Scopus 内容基础上,但偶尔可能会出现差异。Scopus AI 可能会生成被视为不正确、误导、偏见甚至冒犯的结果。Scopus AI 并非旨在提供法律、财务或医疗建议。用户不应单方面依赖 Scopus AI 提供的信息而不进行独立研究。如果您想在工作中使用 Scopus AI 生成的内容,请咨询您的机构或查询工作场所指南。请勿将个人、机密或敏感信息输入 Scopus AI。
The vector search engine is updated in near real time, ensuring that the response you receive always considers the latest relevant research available in the Scopus database.
The capabilities of the large language models (LLMs) used in GenAI tools have captured the world’s attention. However, they also come with shortcomings, including a lack of transparency and hallucinations, which can undermine trust in the information they deliver.
Scopus AI minimizes hallucinations and bias by using only high-quality, curated Scopus content identified by our sophisticated vector search.
Scopus AI shows its workings with clear references to the documents it uses to generate its response. It also tells you how confident it is that the response matches your query.
Scopus AI has been designed to avoid unnecessary data retention. The Elsevier Privacy Policy explains how all of our products collect, use and share your personal information.
The content that Scopus AI draws on is peer reviewed and has been rigorously vetted and selected for inclusion in Scopus by the independent Content Selection and Advisory Board.
Scopus AI has been developed and tested in close collaboration with the academic community to ensure it meets key needs and concerns. We continue to work with researchers to enhance the tool.
Scopus AI moves beyond providing just a simple summary response to offer unique features that enable you to continue exploring and learning.
Scopus AI draws on a unique and powerful blend of technology, including our in-house developed and patent-pending RAG fusion algorithm that improves the quality of the search and responses.
Randomized user testing is one of the many ways that we collect user feedback on Scopus AI.Unfortunately, a user cannot request to be included in user testing because the randomization is a fundamental principle that helps ensure statistical validity.
Scopus AI is now available for your institution to purchase. The exact cost depends on several factors, including whether you are an existing Scopus customer.
If your institution is interested in buying Scopus, Scopus AI, or would like to understand the benefits of combining the two products, please contact your Elsevier account team. New to Elsevier? Visit this page to be connected with an Elsevier representative.
If you are an individual user seeking access to Scopus AI, we recommend reaching out to your library to explore the available options.
在将生成式 AI 嵌入 Scopus 的过程中,我们将遵循“负责任的人工智能原则”和“隐私原则”,与我们的社区合作确保我们的解决方案能够帮助他们实现目标。
我们使用私有 LLM。也就是说,我们没有通过数据交换或使用我们的数据来训练公共模型。这是我们实施的一项重要特性,可为数据出版商和作者提供隐私保障,让他们彻底放心。
The prompt engineering that guides our large language models (LLMs) has been designed to be extremely strict, with clear instructions and scope. For example, the response that Scopus AI generates must match the intent of your query. If the AI can’t find relevant academic papers in Scopus, it must inform you. And when Scopus AI does make a claim or assertion, a reference is always required.
Scopus AI was one of the first products to pioneer what is rapidly becoming the gold standard for LLM use – the retrieval augmented generation (RAG) fusion model. It’s an approach that improves the quality of both vector search retrieval and the generation of LLM summaries.
Scopus AI responses are also regularly tested against two rigorous evaluation frameworks. Together, these factors reduce the risk of hallucinations, and we continue to work on developments to further limit those risks.
We take bias very seriously. Scopus AI draws exclusively on the academic content in Scopus, ensuring transparency by directly referencing the abstracts behind any claims that the tool makes. Our vector search engine employs cosine similarity to identify which abstracts are the closest match to your query rather than favoring the papers that are most cited or published in certain high impact journals. But if your query has a strong bias, it may be reflected in the response. Even if your question is neutral, there may be bias in the Scopus documents that the AI identifies for its response.
One of the ways we attempt to mitigate this is by testing Scopus AI against two rigorous evaluation frameworks. One in particular requires Scopus AI to answer questions linked to areas of potential bias so we can identify and minimize inappropriate responses. And we actively test the service to try and produce responses that create or reinforce unfair bias based on both internal and external queries like Quora’s Insincere Questions Classification.
Our prompt engineering instructs the LLM to filter out 'unsafe' answers that perpetuate prejudice, harm, or stereotypes against individuals from various backgrounds. And where there is bias in a document that Scopus AI uses in a response, it will acknowledge this and provide a reference for the source. We have user-friendly feedback mechanisms so that users can report any harmful or biased responses, which are manually reviewed by our team.
Our current policy is that a GenAI tool cannot be listed or cited as an author, as it is unable to accept responsibility and accountability for its work. In the case of Scopus AI, it is a great learning aid to help you get familiar with a new topic and suggest avenues of exploration.
Our guidance for authors, reviewers and editors permits the use of GenAI tools to improve the readability and language of the research article, but emphasizes that:
The technology should always be applied as a support tool with human oversight and control.
Results should always be carefully reviewed and edited, where necessary.
Authors should declare if and how they have used a GenAI tool in their paper.
Scopus AI is designed to provide an overview or introduction into a subject or topic based on real academic information. It is not designed to be an absolute source of truth but a guide. For this reason, we recommend that users aim to cite papers directly from the citations in the summaries, rather than citing the summaries themselves.
Further, Scopus AI doesn’t currently include versioning, so the summaries are not suitable for citing.
We will continue to review this position as the technologies mature. Please note the guidance we link to above only refers to the use of AI tools in the writing/editorial process, and not to the use of AI tools to analyze and draw insights from data as part of the research process.
Not at the moment, but we are already exploring ways we can enable users to enter queries in their language of choice. Longer term, we will continue working with researchers to understand how expanding the tool’s language capabilities might benefit them.
了解更多关于 Scopus AI 的信息,以及推动最近发表的这些文章的技术。
精选文章和资源
文章:Breaking academic barriers: language models and the future of search(打破学术壁垒:语言模型与搜索的未来)(在新选项卡/窗口中打开)(在新的选项卡/窗口中打开),作者 Adrian Raudaschl,《泰晤士高等教育》,2023 年 10 月
文章:Responsible AI and the many dimensions of artificial intelligence(负责任的人工智能和人工智能的多个维度),作者 Max Voegler 博士,Elsevier Connect,2023 年 5 月
报告:Apprehension of Generative AI in Higher Education Overstated(对高等教育中生成式人工智能的理解被夸大了)(在新选项卡/窗口中打开)(在新的选项卡/窗口中打开),Cengage Survey Finds,Cengage Group,2023 年 8 月
参加我们即将举行的 Scopus AI 系列网络研讨会,或观看以往会议的录音。
The upcoming Choice (by ACRL(在新的选项卡/窗口中打开)) webinar will focus on how Scopus AI empowers interdisciplinary collaboration, demystifies emerging fields, helps identify research partners, and uncovers promising areas for exploration. Gain practical insights into transparency, reliability, accuracy, and relevance of results.
This session will spotlight the Top 5 use cases for generative AI for researchers, showcasing how this groundbreaking technology can expedite research processes and enhance the accuracy of outputs. Whether you're a researcher keen on fully harnessing Scopus AI, or a research leader looking to integrate more tech-forward practices, this webinar will provide you with valuable insights and practical advice.
Tue, Jun 04
11:00 AM - 12:00 PM GMT+8
Explore how Scopus data can be used to inform a generative AI solution to support researchers. Topics include content selection, bias minimization, content integrity, quality and accuracy assurance, and Scopus content used to train AI.
Watch the recording(在新的选项卡/窗口中打开)
Learn how we addressed ethical implications, quality control, and fairness concerns during the development of Scopus AI.
Watch the recording(在新的选项卡/窗口中打开)
Discover how researchers can effectively use Scopus AI throughout the research journey and learn practical ways to leverage our Gen AI-informed results for an accelerated search process.