Unverified50% confidenceFactExact time
The decision model takes a state and up to five typed questions (noul/choice/score) and returns answers and confidence in a single forward pass, generating no text, so output_tokens is 0.
1
Sources
50%
Confidence
Long-term
Relevance
10/13/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen the retrieval context does not contain the answer, many language models fill the gap with plausible-sounding content, which is exactly the hallucination users notice; fixes include instructing the model to answer only from the provided context, giving it a clear way to opt out, requiring a citation for every claim, setting a retrieval score threshold, and logging rejected questions.70% similarUnverifiedAn output parser filling in default values when it encounters a malformed response leaves downstream code unable to distinguish whether a field was produced by the model or fabricated by the parser, which is a silent failure mode.67% similarUnverified针对特定触发词的后门攻击可让模型在大多数情况下表现正常，仅在遇到特定输入时才输出预设错误信息，使常规评测基准难以捕捉64% similarUnverifiedSemantic caching bypasses the model call entirely when a new query is sufficiently similar to an already-answered query, but carries the trade-off of returning incorrect answers to subtly different questions.64% similarUnverified不提供上下文时，本地小模型对领域问题会拒绝回答或产生幻觉，引入 RAG 后能给出准确答案63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1016981API
curl https://kongchang.com/api/v1/knowledge/claims/1016981MCP
get_claim(id=1016981)