arXiv:2602.22221v2 Announce Type: replace-cross Abstract: Search engines and AI-powered systems increasingly mediate access to factual information, yet their reliability remains difficult to evaluate in realistic information-seeking settings. We study this problem in the Chinese web ecosystem by constructing a query-based fact-checking dataset from real Chinese search logs and comparing nine systems across traditional search engines, standalone large language models, and search-integrated AI Overviews. Focusing on factual Chinese-language factual Yes/No questions, we evaluate whether systems p
The proliferation of AI-powered search and information systems, particularly in geopolitically sensitive regions like China, necessitates immediate evaluation of their reliability and potential biases.
Understanding reliability asymmetries in factual search and AI answers, especially in the context of the Chinese information ecosystem, provides critical insights into information control, AI ethics, and geopolitical influence.
This study establishes a methodology to quantify reliability in Chinese AI search, revealing potential biases and vulnerabilities that differentiate it from Western counterparts.
- · Academic researchers
- · Ethical AI developers
- · Information integrity advocates
- · Platforms with biased AI
- · Users relying on unreliable information
- · Global consensus on factual information
The findings will inform the development of more robust evaluation methods for AI systems across different linguistic and cultural contexts.
Increased scrutiny of national AI systems could lead to policy discussions around mandated transparency and accountability for AI-generated content reliability.
Divergent reliability standards in AI answers might exacerbate information 'splinternet' effects, fostering distinct versions of 'truth' across geopolitical blocs.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL