Machine Understanding of Scientific Language

2025-06-30

AI Summary

This study addresses the challenge of identifying misleading scientific claims amid an overwhelming volume of scientific text. Methodologically, it introduces an automated framework for assessing the credibility of science communication by innovatively integrating verifiable scientific claim identification, adversarial statement generation, zero-shot fact-checking, and scientific information evolution modeling—augmented with few-shot learning, multi-source domain adaptation, and crowdsourced label learning. The contributions are threefold: (1) a novel model achieving high-precision detection of misleading statements under limited labeled data—the first of its kind; (2) the first interpretable, dynamic modeling of scientific claim credibility over time; and (3) data-driven insights into science communication mechanisms, directly supporting evidence-based misinformation governance.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Mitigating misinformation and disinformation

Abstract

Scientific information expresses human understanding of nature. This knowledge is largely disseminated in different forms of text, including scientific papers, news articles, and discourse among people on social media. While important for accelerating our pursuit of knowledge, not all scientific text is faithful to the underlying science. As the volume of this text has burgeoned online in recent years, it has become a problem of societal importance to be able to identify the faithfulness of a given piece of scientific text automatically. This thesis is concerned with the cultivation of datasets, methods, and tools for machine understanding of scientific language, in order to analyze and understand science communication at scale. To arrive at this, I present several contributions in three areas of natural language processing and machine learning: automatic fact checking, learning with limited data, and scientific text processing. These contributions include new methods and resources for identifying check-worthy claims, adversarial claim generation, multi-source domain adaptation, learning from crowd-sourced labels, cite-worthiness detection, zero-shot scientific fact checking, detecting exaggerated scientific claims, and modeling degrees of information change in science communication. Critically, I demonstrate how the research outputs of this thesis are useful for effectively learning from limited amounts of scientific text in order to identify misinformative scientific statements and generate new insights into the science communication process

Problem

• Identify faithfulness of scientific text automatically
• Develop methods for machine understanding of scientific language
• Detect misinformative scientific statements with limited data

Innovation

• Automatic fact checking for scientific claims
• Learning with limited data via domain adaptation
• Zero-shot scientific fact checking techniques