New Model Extracts Sentence-level Proof to Verify Events, Boosting Fact-checking Accuracy for Journalists, Legal Teams, and Policymakers
July 1, 2025
Introduction:
(Eurekalert) Imagine reading a long article or a thick legal contract and knowing, with confidence, exactly which lines prove that an event happened—or did not happen. That is now possible thanks to a research team at Soochow University. They have built a new neural network that not only determines if an event described in a document is real but also highlights the exact sentences that led it to that conclusion. In head-to-head comparisons with earlier approaches, this new model improved overall fact-checking accuracy by 2.5 points and exact-match accuracy by almost 5 points on a standard benchmark.
“We aimed to open the black box of AI decision-making,” says Prof. Zhong Qian, the lead researcher. “By showing exactly which sentences support our model’s verdict, we make its reasoning as clear as stepping through a well-explained proof.”
Why This Makes a Difference
In our fast-paced digital world, false or misleading claims can spread rapidly. Journalists racing to cover breaking stories need tools that do not simply raise a flag but also explain their reasoning. Legal teams reviewing lengthy contracts cannot afford to miss a single misleading clause. This model’s ability to pinpoint the precise text that supports—or contradicts—an event’s truth helps professionals across fields see exactly why a claim stands or falls. It is a step toward AI systems that feel less like inscrutable black boxes and more like transparent partners.
Additional extract:
This work appears in the June 2025 issue of Frontiers of Computer Science. The authors plan to share their code and detailed annotations, allowing others to build upon their outcomes. As AI becomes a crucial part of our daily lives, innovations like this one promise to keep machines honest, transparent, and valuable—whether we are checking the latest news, reviewing a contract, or simply reading for pleasure.
Accelerating Science with AI By Alyssa Schaechinger
July 24, 2025
Introduction:
(Eureklaert) It can take years for humans to solve complex scientific problems. With AI, it can take a fraction of the time.
Dr. Shuiwang Ji, a professor in the Department of Computer Science and Engineering at Texas A&M University and a leading expert in the emerging field of AI for science and engineering — commonly referred to as AI4Science — is at the forefront of using AI to accelerate scientific problem solving.
Ji, along with other Texas A&M researchers, has recently published a paper in Foundations and Trends in Machine Learning outlining the uses and benefits of AI4Science. This collaborative paper features more than 60 authors from 15 universities, and contains over 500 pages of information on using AI for science.
The paper highlights the importance of using AI to solve complex equations, which can be applied to many different areas of science and engineering. For example, the famed Schrodinger’s equation can be solved with AI, improving efficiency and accuracy in many research areas, including drug discovery, material design, battery materials, and catalyst design.
“The goal of natural sciences is to understand the world on different temporal and physical scales, leading to three main systems: quantum, atomic, and continuum,” said Ji, who is also a Presidential Impact Fellow and Chancellor EDGES Fellow. “The fundamentals of these systems are ruled by differential equations, but the complexity of these equations significantly increases as the systems grow.”
