Unverified50% confidenceFactExact time
When generating text, AI models may "fabricate" plausible-looking citations, including authors, titles, dates, and URLs, based on patterns in the training data; this phenomenon is called "hallucinated citation."
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
AI-Assisted Paper Cites Nonexistent TorrentFreak Article: Academic Integrity Concerns Resurface
hackernewshackernews10/24/2026
Related Entities
Related Claims
Unverified大语言模型会编造看似真实、实则不存在的文献引用，这种现象被称为「引用幻觉」（citation hallucination）75% similarVerifiedThe reason large language models fabricate references is that they generate text based on probability rather than database retrieval, a phenomenon known as AI hallucination.73% similarUnverifiedThe "citation" mechanism in LLM structured extraction requires the model, when outputting each extracted field, to provide the verbatim source snippet in the original document for that value, based on the theoretical rationale that accurately copying source text reduces hallucination risk.69% similarUnverifiedRequiring the model in the prompt to tag a source ID after each sentence, or using structured output to return answer and citations, are two ways to force citations at generation time.69% similarUnverified使用整数标签映射可以立即捕获幻觉引用——当模型引用未发送的标签时即被检测出来67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1093090API
curl https://kongchang.com/api/v1/knowledge/claims/1093090MCP
get_claim(id=1093090)