大模型
arxiv.org ·
转录压缩对基于 LLM 的日本 YouTube 视频医疗错误信息检测的影响
该 arXiv 预印本研究转录压缩如何影响 LLM 对日语医疗 YouTube 视频的真伪分类。作者比较四种输入设计：完整转录、LLM 生成摘要、基于 RAPTOR 的检索增强生成（RAG）以及抽取候选医学健康句的 Screening，使用 74 条标注为 Real 或 Fake 的长视频评估分类性能，并用 J-LIWC、模糊表达和机构/技术术语做语言分析。结果显示完整转录基线表现最佳，所有压缩输入都增加假阴性，即 Fake 视频更易被误判为 Real；摘要导致最大性能下降，Screening 在压缩方案中最好但仍遗漏大量医学相关句。语言分析表明错误并非源于确定性表达简单增加，而是摘要削弱了情感、社会、时间、认知和会话线索，摘要与 RAG 使机构和技术术语更突出，可能让 Fake 视频显得更连贯、更具权威性，从而削弱错误信息检测所需线索。
AI推荐理由 arXiv 预印本，作者与摘要明确，实验设计可核查：74 条日语长视频、四类转录输入（全文、LLM 摘要、RAPTOR RAG、Screening）对比。核心新信息是全文基线最优，所有压缩输入都增加假阴性（假视频更易被判为真），摘要降幅最大，Screening 在压缩方案中最好但仍漏掉大量医学相关句；语言分析显示摘要削弱情感、社会、时间、认知与会话线索，摘要与 RAG 反而使机构和技术术语更突出。局限是仅限日语医学 YouTube、样本 74 条、预印本未经同行评审，结论不能外推到其他语言或领域。
72
正文
Computer Science > Computation and Language
arXiv:2609.30882 (cs)
[Submitted on 25 Sep 2026]
Title:Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos
Authors:Yuya Wake, Sho Tsugawa, Toshiyuki Amagasa
View a PDF of the paper titled Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos, by Yuya Wake and 2 other authors
View PDF
HTML (experimental)
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
Comments:
Subjects:
Computation and Language (cs.CL)
Cite as:
arXiv:2609.30882 [cs.CL]
(or
arXiv:2609.30882v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.30882
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Yuya Wake [view email]
[v1]
Fri, 25 Sep 2026 06:42:44 UTC (20 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Effects of Transcript Compression on LLM-based Medical Misinformation Detection in Japanese YouTube Videos, by Yuya Wake and 2 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)