Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking
arXiv:2501.18265 · doi:10.1145/3726302.3729960
Abstract
Evaluating the truthfulness of online content is critical for combating misinformation. This study examines the efficiency and effectiveness of crowdsourced truthfulness assessments through a comparative analysis of two approaches: one involving full-length webpages as evidence for each claim, and another using summaries for each evidence document generated with a large language model. Using an A/B testing setting, we engage a diverse pool of participants tasked with evaluating the truthfulness of statements under these conditions. Our analysis explores both the quality of assessments and the behavioral patterns of participants. The results reveal that relying on summarized evidence offers comparable accuracy and error metrics to the Standard modality while significantly improving efficiency. Workers in the Summary setting complete a significantly higher number of assessments, reducing task duration and costs. Additionally, the Summary modality maximizes internal agreement and maintains consistent reliance on and perceived usefulness of evidence, demonstrating its potential to streamline large-scale truthfulness evaluations.
19 pages; 7 figures; 5 tables
References in corpus (10)
- The science of fake news
- A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
- Factuality Challenges in the Era of Large Language Models
- End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models
- Crowdsourced Fact-Checking at Twitter: How Does the Crowd Compare With Experts?
- The Many Dimensions of Truthfulness: Crowdsourcing Misinformation Assessments on a Multidimensional Scale
- Human-centered NLP Fact-checking: Co-Designing with Fact-checkers using Matchmaking for AI
- Scalable Fact-checking with Human-in-the-Loop
- Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
- Can Community Notes Replace Professional Fact-Checkers?