Unverified50% confidenceFactExact time
LLMs inject entities that do not exist at all or terms irrelevant to the topic when generating query expansion terms; these hallucinated terms increase ranking noise and can harm retrieval effectiveness.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe hallucinated output of LLMs is formally almost indistinguishable from correct content—fluent in expression and internally consistent in logic—making it harder to raise readers' guard.72% similarUnverifiedLLM 的真正优势在于处理模糊性、非结构化和开放性问题，如自然语言理解与生成、从杂乱文本抽取语义信息70% similarUnverifiedLLMs tend to over-literally interpret examples in prompts, treating them as hard rules rather than reference semantics.70% similarUnverifiedUsing an LLM to perform style transformation and expansion on existing corpora is more reliable than letting it freely generate prompts.70% similarUnverifiedWhen non-textual information (such as images, tables, code, and sensor data) is input into an LLM, it often must first be serialized into textual descriptions, resulting in information loss and token waste.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1002083API
curl https://kongchang.com/api/v1/knowledge/claims/1002083MCP
get_claim(id=1002083)