Tag:Hallucination

Most agents never say "I don't know." They were trained on benchmarks that reward a confident guess over an honest abstention, so in production they invent a policy, a number, or a citation and say it with a straight face. An abstention gate fixes that: a cheap confidence signal, a threshold you calibrate against a real error budget, and a decision to answer, defer, or escalate. This is how you get an agent that knows its own limits.

Your retrieval is good. The right chunks come back, the citation links resolve, and the answer reads clean. Then a user clicks the citation and the document says nothing of the kind. The model wrote a confident claim, stapled a real source to it, and shipped. A grounding gate catches that before the user does.