News

Aug 18, 2023

ChatGPT

You can also search for this author in PubMed Google Scholar You have full access to this article via your institution. AI chatbots such as ChatGPT are being linked with scientific databases to create

You can also search for this author in PubMed Google Scholar

You have full access to this article via your institution.

AI chatbots such as ChatGPT are being linked with scientific databases to create conversational search experiences.Credit: Gabby Jones/Bloomberg via Getty

The conversational AI-powered chatbots that have come to Internet search engines, such as Google’s Bard and Microsoft’s Bing, look increasingly set to change scientific search too. On 1 August, Dutch publishing giant Elsevier released a ChatGPT-powered AI interface for some users of its Scopus database, while British firm Digital Science announced a closed trial of an AI large language model (LLM) assistant for its Dimensions database. Meanwhile, US firm Clarivate says it’s also working on bringing LLMs to its Web of Science database.

LLMs for scientific search aren’t new: start-up firms such as Elicit, Scite, and Consensus already have such AI systems, which help to summarize a field’s findings or identify top studies, relying on free science databases or (in Scite’s case) access to paywalled research articles through partnerships with publishers. But firms who own large proprietary databases of scientific abstracts and references are now joining the AI rush.

Elsevier’s chatbot, called Scopus AI and launched as a pilot, is intended as a light, playful tool to help researchers quickly get summaries of research topics they’re unfamiliar with, says Maxim Khan, an Elsevier executive in London who oversaw the tool’s development. In response to a natural-language question, the bot uses a version of the LLM GPT-3.5 to return a fluent summary paragraph about a research topic, together with cited references, and further questions to explore.

In response to a text-based question, Scopus AI returns a fluent summary of a research topic as well as relevant references.Credit: Scopus AI

A concern about LLMs for search — especially scientific search — is that they are unreliable. LLMs don’t understand the text they produce; they work simply by spitting out words that are stylistically plausible. Their output can contain factual errors and biases and, as academics have quickly found, can make up non-existent references.

The Scopus AI is therefore constrained: it has been prompted to generate its answer only by reference to five or ten research abstracts. The AI doesn’t find those abstracts itself: rather, after the user has typed in a query, a conventional search engine returns them as relevant to a question, explains Khan.

Many other AI search engine systems adopt a similar strategy, notes Aaron Tay, a librarian at Singapore Management University who follows AI search tools. This is sometimes termed retrieval-augmented generation, because the LLM is limited to summarizing relevant information that another search engine retrieves. “The LLM can still occasionally hallucinate or make things up,” says Tay, pointing to research on Internet search AI chatbots, such as Bing and Perplexity, that use a similar technique.

Elsevier has limited its AI product to search only for articles published since 2018, so as to pick up recent papers, and has instructed its chatbot to appropriately cite the returned abstracts in its reply, to avoid unsafe or malicious queries, and to state if there’s no relevant information in the abstracts it receives. This can’t avoid mistakes, but minimizes them. Elsevier has also cut down the unpredictability of its AI by picking a low setting for the bot’s ‘temperature’ — a measure of how often it chooses to deviate from the most plausible words in its response.

Might users simply copy and paste the bot’s paragraphs into their own papers, effectively plagiarizing the tool? That’s a possibility, says Khan. Elsevier has so far tackled this with guidance that asks researchers to use the summaries responsibly, he says. Khan points out that funders and publishers have issued similar guidance, asking for transparent disclosure if LLMs are used in, for instance, writing papers or conducting peer reviews, or in some cases stating that LLMs shouldn’t be used at all.

For the moment, the tool is being rolled out only to around 15,000 users, a subset of Scopus subscribers, with other researchers invited to contact Elsevier if they want to try it. The firm says it expects a full launch in early 2024.

Also on 1 August, Digital Science announced that it was introducing an AI assistant for its large Dimensions scientific database, at the moment only for selected beta testers. Rather as with Scopus AI, after a user types in their question, a search engine first retrieves relevant articles, and an Open AI GPT model then generates a summary paragraph around the top-ranked abstracts that have been retrieved.

“It’s remarkably similar, funnily enough,” says Christian Herzog, the chief product officer for the firm. (Digital Science is part of Holtzbrinck Publishing Group, the majority shareholder in Nature’s publisher, Springer Nature.)

Dimensions also uses the LLM to provide some more details about relevant papers, including short rephrased summaries of their findings.

Herzog says the firm hopes to release its tool more widely by the end of the year, but is for the moment working with scientists, funders and others who use Dimensions to test where LLMs might be useful — which still remains to be seen. “This is about gradually easing into a new technology and building trust,” he says.

Tay says he’s looking forward to tools that use LLMs on the full text of papers, and not just abstracts. Sites such as Elicit already let users use LLMs to answer detailed questions about a paper’s full text — when the bots have access to it, as with some open-access articles, he notes.

At Clarivate, meanwhile, Bar Veinstein, president of what the firm calls its ‘academia and government segment’, says the company is “working on adding LLM-powered search in Web of Science”, referring to a strategic partnership signed with AI21 Labs, based in Tel Aviv, Israel, that the firms announced in June. Veinstein did not give a timeline for the release of an LLM-based Web of Science tool, however.

doi: https://doi.org/10.1038/d41586-023-02470-3

Reprints and Permissions

AI science search engines are exploding in number — are they any good?

AI chatbots are coming to search engines — can you trust the results?

What ChatGPT and generative AI mean for science

Scientific discovery in the age of artificial intelligence

Review Article 02 AUG 23

AI search of Neanderthal proteins resurrects ‘extinct’ antibiotics

News 28 JUL 23

AI helps scientists to eavesdrop on endangered pink dolphins

News 27 JUL 23

Ancient DNA reveals the living descendants of enslaved people through 23andMe

News 03 AUG 23

Mega-scale experimental analysis of protein folding stability in biology and design

Article 19 JUL 23

Fourteen things you need to know about collaborating with data scientists

Career Column 13 JUL 23

Ancient DNA reveals the living descendants of enslaved people through 23andMe

News 03 AUG 23

Data sharing: putting Nature’s policy to the test

Correspondence 25 JUL 23

Medicine is plagued by untrustworthy clinical trials. How many studies are faked or flawed?

News Feature 18 JUL 23

The Chinese University of Hong Kong CUHK Vice-Chancellor Early Career Professorships The Chinese University of Hong Kong (CUHK), a comprehensive re...

Hong Kong (HK)

The Chinese University of Hong Kong

Located in the beautiful coastal city of Dalian, surrounded by mountains and sea, DICP seeks all talents from around the globe.

Dalian, Liaoning, China

The Dalian Institute of Chemical Physics (DICP)

We’re seeking a geophysicist with a strong background in either geodynamics, seismology or structural geology to join our team.

Beijing, Hong Kong, Jersey City, Nanjing, New York, Philadelphia, Shanghai or Washington DC (hybrid)

Springer Nature Ltd

The Chan Lab in the Human Oncogenesis & Pathogenesis Program at Memorial Sloan Kettering Cancer Center is seeking a highly motivated and successful...

New York City, New York (US)

Memorial Sloan Kettering Cancer Center

The professorship is associated with the management of a department in the field of vegetative physiology.

Tübingen, Baden-Württemberg (DE)

University of Tübingen – Faculty of Medicine