Unverified50% confidenceFactExact time
General-purpose large models are prone to generating hallucinatory code in specialized scenarios such as DOCA, such as calling non-existent interfaces or using incorrect parameters.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/1/2026
First Seen
Valid until: 12/30/2026
Sources
Related Entities
Related Claims
UnverifiedNot all models or platforms support custom tool calls, and in unsupported environments the DFS logic can degrade to a plain-text numbered list interaction.61% similarUnverifiedIn programming scenarios, models may fabricate non-existent API functions, invent version numbers for libraries, or produce code solutions with logical flaws.60% similarVerifiedLarge language models have hallucination defects in code generation scenarios, manifested as referencing non-existent library functions and generating syntactically correct but logically erroneous code.59% similarUnverifiedLLM 自动生成文档可能包含幻觉，将不存在的设计意图写入文档，进而误导依赖这些文档工作的 AI 智能体58% similarUnverified大语言模型使非结构化的自然语言可以直接作为执行输入，无需遵循 BDD 工具的特定语法58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/965964API
curl https://kongchang.com/api/v1/knowledge/claims/965964MCP
get_claim(id=965964)