Efficiency and Effectiveness of LLM-Based Summarization of Evidence in Crowdsourced Fact-Checking

TL;DR

This study shows that using LLM-generated summaries of evidence in crowdsourced fact-checking maintains accuracy while significantly improving efficiency and reducing costs.

Contribution

It introduces and evaluates a summarization-based approach for evidence in crowdsourced fact-checking, demonstrating its effectiveness and efficiency benefits.

Findings

Summarized evidence achieves comparable accuracy to full evidence.

Summarization increases assessment throughput and reduces costs.

Participants find summarized evidence useful and reliable.

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.