Unverified50% confidenceFactExact time
The document acknowledges that "instructions to avoid sycophancy do not reliably eliminate it", and user framing may still influence the model's surface conclusions.
1
Sources
50%
Confidence
Long-term
Relevance
10/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGrounding prompts that instruct the model to answer only based on provided documents and cite the relevant passages can greatly reduce the probability of fabrication, but cannot eliminate it entirely.73% similarUnverifiedOnce injected content contains sensitive information or false premises, the model may still repeat it to the customer, so one cannot rely on the model to ignore irrelevant injections.70% similarUnverifiedThe model endpoint may retain prompts according to policies the user has not read.70% similarUnverifiedDownstream users' fine-tuning of a model may inadvertently break its original safety properties.68% similarUnverifiedWhen 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.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1092523API
curl https://kongchang.com/api/v1/knowledge/claims/1092523MCP
get_claim(id=1092523)