The Next Phase of Scientific Fact-Checking: Advanced Evidence Retrieval from Complex Structured Academic Papers
arXiv:2506.20844 · doi:10.1145/3731120.3744614
Abstract
Scientific fact-checking aims to determine the veracity of scientific claims by retrieving and analysing evidence from research literature. The problem is inherently more complex than general fact-checking since it must accommodate the evolving nature of scientific knowledge, the structural complexity of academic literature and the challenges posed by long-form, multimodal scientific expression. However, existing approaches focus on simplified versions of the problem based on small-scale datasets consisting of abstracts rather than full papers, thereby avoiding the distinct challenges associated with processing complete documents. This paper examines the limitations of current scientific fact-checking systems and reveals the many potential features and resources that could be exploited to advance their performance. It identifies key research challenges within evidence retrieval, including (1) evidence-driven retrieval that addresses semantic limitations and topic imbalance (2) time-aware evidence retrieval with citation tracking to mitigate outdated information, (3) structured document parsing to leverage long-range context, (4) handling complex scientific expressions, including tables, figures, and domain-specific terminology and (5) assessing the credibility of scientific literature. Preliminary experiments were conducted to substantiate these challenges and identify potential solutions. This perspective paper aims to advance scientific fact-checking with a specialised IR system tailored for real-world applications.
arXiv commentAccepted for ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR'25)
References in corpus (9)
- BioSentVec: creating sentence embeddings for biomedical texts
- Citation Recommendation: Approaches and Datasets
- End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models
- Scim: Intelligent Skimming Support for Scientific Papers
- Ranked List Truncation for Large Language Model-based Re-Ranking
- "In-Context Learning" or: How I learned to stop worrying and love "Applied Information Retrieval"
- Stopping Methods for Technology Assisted Reviews based on Point Processes
- Joint Verification and Reranking for Open Fact Checking Over Tables
- RLStop: A Reinforcement Learning Stopping Method for TAR