GENERATIVE-AI-LEADER Question #28: Real Exam Question with Answer & Explanation

Question

A global news company is using a large language model to automatically generate summaries of news articles for their website. The model's summary of an international summit was accurate until it hallucinated by stating a detail that did not occur. How should the company overcome this hallucination?

Options

• AImplement stricter safety settings to filter out potentially controversial topics.
• BFine-tune the model on a larger dataset of news articles.
• CIncrease the temperature setting of the model to encourage more diverse outputs.
• DUse grounding to base the model output on the source articles.

Explanation

The core problem is the model's hallucination--it invented a factual detail--in a context (news reporting) where factual accuracy is non-negotiable. To correct a factual error in a generative summary, the model must be constrained to speak only based on verifiable facts from a reliable The most effective technique to combat hallucinations and ensure factual adherence is Grounding (D). Grounding connects the Large Language Model's (LLM's) output to a specific, trusted, and verifiable source of information. This is often implemented using Retrieval- Augmented Generation (RAG). In this scenario, grounding the summary model on the original source articles ensures that every generated statement is directly entailed by the provided facts (the source article content).

No community discussion yet for this question.