Can AI help researchers explore scientific findings? A new tool puts it to the test
Reading a scientific article is one thing. Exploring the data behind it is another. Even when a research article provides access to its supporting data sets, answering a follow-up question often requires downloading files, understanding their structure and writing code.
by Sandra Niemeyer, Leibniz Information Centre for Science and Technology
edited by Swati Mestri, reviewed by Alexander Pol
This article has been reviewed according to Science X's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:
Add to Preferred Sources Credit: Unsplash/CC0 Public Domain Reading a scientific article is one thing. Exploring the data behind it is another. Even when a research article provides access to its supporting data sets, answering a follow-up question often requires downloading files, understanding their structure and writing code.
Researchers at the TIB are working to bridge this gap. A new tool, described in a paper presented at the 2026 ACM/IEEE Joint Conference on Digital Libraries (JCDL), lets users explore research data by asking questions in plain language. This work offers a practical approach to making research evidence easier to explore, visualize and reuse.
Developed by Hadi Ghaemi, Zakieh Alizadehsani and Markus Stocker, the tool builds on the TIB Knowledge Loom, an open science digital library that connects scientific statements with supporting data, code and methods.
The research is published in Proceedings of the 26th ACM/IEEE Joint Conference on Digital Libraries.
The tool takes these connections a step further by letting users query and explore the supporting data through a plain-language question-and-answer interface.
In addition to answering users' questions, the tool allows them to explore the supporting data, view the results in tables and, where appropriate, as visualizations, and see how the results were produced.
A user might want to reproduce a reported result, compare groups within a data set or explore a trend the original article did not discuss. The system uses artificial intelligence (AI) to translate the question into a database query, runs it against the supporting data and returns a table. When helpful, the tool can also visualize the data. Users can also inspect the query to see how the result was produced.
A key challenge for the AI running this tool is ensuring it consults the right data. While testing the tool, the researchers found that linking each question to the data set associated with a specific scientific finding eliminated errors caused by the AI consulting the wrong data set. It also improved the accuracy of the AI's answers.
However, pointing the AI to the right data set does not guarantee a trustworthy response. The main workflow answered only about 62%–67% of questions correctly. The results highlight both the promise of easier data exploration and the continuing need for users to check whether an analysis answers their scientific question.
For researchers, the practical benefit is clear. When scientific findings are linked to their supporting data, users can explore differences, compare observations or investigate trends through plain-language questions. Because the tool shows the database query it automatically generated to answer the question, users can inspect how an answer was produced, which supports transparency and reproducibility.
Hadi Ghaemi et al., SciClaim2Explore: Claim-Guided Exploration of Scientific Data Evidence, Proceedings of the 26th ACM/IEEE Joint Conference on Digital Libraries (2026). DOI: 10.1145/3805696.3846517 Key concepts Large language models AI alignment Human-centered AI interfaces Agentic consumer AI Generative AI ethics Provided by Leibniz Information Centre for Science and Technology Who's behind this story? Swati Mestri Swati Mestri holds a bachelor's degree in Electronics Engineering and has worked as a content editor since 2019. She has experience editing research documents across technology, health care, and materials science, and has a particular interest in technology and space. Full profile →
PhD nano-engineering from Delft University. Published researcher and journal reviewer. Brings scientific insight to content standards. Full profile →