Unverified50% confidenceOpinionExact time
The PLML proposal points out that the problem is not whether conversation data is stored, but whether the right information can be retrieved and supplied to the model at the right moment.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
Unverified如果信息不在对话历史里,模型就不知道它;对于私有代码库模型一无所知,除非通过工具调用探索或通过CLAUDE.md、AGENTS.md等文件注入上下文67% similarUnverifiedLarge language models still face hallucination problems in information extraction tasks, potentially completing information not explicitly mentioned in conversations and causing inaccurate CRM data.59% similarUnverifiedAbsence verification requires the model to actively infer which important information that should have appeared in the source material was omitted, necessitating the prior construction of a complete mental model of what ought to be present, which is far more difficult for LLMs.59% similarUnverified端到端模型在代表性充足与代表性不足口音之间的WER差距并未按比例缩小,属于数据分布问题而非架构问题58% similarUnverifiedChat context is not a reliable state store—it gets truncated, summarized, and reinterpreted, and cannot serve as a source of truth for long-term projects.57% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070574API
curl https://kongchang.com/api/v1/knowledge/claims/1070574MCP
get_claim(id=1070574)