Can a Hallucinating Model help in Reducing Human "Hallucination"?
원문 초록
The prevalence of unwarranted beliefs, spanning pseudoscience, logical fallacies, and conspiracy theories, presents substantial societal hurdles and the risk of disseminating misinformation. Utilizing established psychometric assessments, this study explores the capabilities of large language models (LLMs) vis-a-vis the average human in detecting prevalent logical pitfalls. We undertake a philosophical inquiry, juxtaposing the rationality of humans against that of LLMs. Furthermore, we propose methodologies for harnessing LLMs to counter misconceptions, drawing upon psychological models of persuasion such as cognitive dissonance theory and elaboration likelihood theory. Through this endeavor, we highlight the potential of LLMs as personalized misinformation debunking agents.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
When Thinking LLMs Lie: Unveiling the Strategic Deception in Representations of Reasoning Models
TrumorGPT: Graph-Based Retrieval-Augmented Large Language Model for Fact-Checking
A Comprehensive Analysis for Visual Object Hallucination in Large Vision-Language Models
Leveraging Context for Multimodal Fallacy Classification in Political Debates
Mitigating Object Hallucinations via Sentence-Level Early Intervention
Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors
토론
이 논문과 연결된 포럼 글이 아직 없습니다.