Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos

Full transcripts outperformed all compressed transcript inputs for LLM-based veracity classification of Japanese medical YouTube videos, according to an arXiv study (arXiv:2609.30882v1) that tested 74 long-form videos labeled Real or Fake. LLM-generated summaries caused the largest performance drop, while RAPTOR-based retrieval-augmented generation and Screening, which extracts candidate medical and health-related sentences, also increased false negatives, meaning Fake videos were more often misclassified as Real. J-LIWC, hedge-expression and institutional/technical-term analyses indicated compression made Fake videos appear more coherent and authoritative rather than simply more certain.

arXiv:2609.30882v1 Announce Type: new Abstract: Large language models LLMs are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are provided in full or compressed through summarization, retrieval, or claim screening. This study examines how such transcript compression affects LLM-based veracity classification of Japanese medical YouTube videos. We compare four transcript input designs: full transcripts, LLM-generated summaries, RAPTOR-based retrievalaugmented generation RAG , and Screening, which extracts candidate medical and health-related sentences. Using 74 long-form videos labeled as Real or Fake, we evaluate classification performance and analyze linguistic changes using J-LIWC, hedge expressions, and institutional or technical terms. The full-transcript Baseline achieved the best performance, whereas all compressed inputs increased false negatives, meaning that Fake videos were more likely to be misclassified as Real. Summary caused the largest performance drop, while Screening performed best among the compressed inputs but still omitted many medically relevant sentences. Linguistic analyses showed that these errors were not explained by a simple increase in certainty. Instead, Summary reduced affective, social, temporal, cognitive, and conversational cues, while Summary and RAG made institutional and technical terms more salient. These findings suggest that transcript compression can represent Fake videos as more coherent and authoritative inputs, thereby weakening cues needed for misinformation detection