A team's Foundry-deployed support chatbot occasionally invents policy details that are not in the company's actual documentation, even though a retrieval step supplies relevant passages with each question. To reduce these fabricated answers, which two changes should the team make? (Select TWO.)

The correct changes are adding an explicit instruction in the system message telling the model to answer only from the supplied passages and to say it does not know when the passages do not cover the question, and verifying that the retrieval step is actually returning the most relevant passages. Explicitly instructing the model to answer only from the supplied passages and to admit when it does not know closes off the model's tendency to fill gaps with plausible-sounding invention. Checking that retrieval actually surfaces the most relevant passages addresses the other common cause: if the model is not given the right grounding text in the first place, it has no choice but to fall back on its own guesses. Increasing the model's maximum output token limit is incorrect because it only allows longer responses; it does nothing to anchor those responses in the actual documentation and could give the model more room to elaborate on fabricated details. Removing the retrieval step entirely is incorrect because it eliminates the one mechanism that grounds answers in company-specific facts, which would make fabrication worse, not better, since the model would be answering purely from general training data with no connection to actual policy. Tightening the instructions and verifying the quality of what gets retrieved are the two changes that directly target why the chatbot is inventing details despite having a retrieval step in place.