AI and Deep Learning

Can we blame the "hallucination" of AI on the poor design of modern RAG systems?

JE Asked by Jeffrey Alexander · 12-01-2025
0 upvotes 17,329 views 0 comments
The question

Every time my chatbot makes something up, I look at the source documents and realize the retrieval failed. Why are RAG systems still so prone to fetching the wrong info? Is it a fundamental flaw in the architecture or just poor implementation by the developers?

3 answers

0
PA
Answered on 14-01-2025

Hallucination is often a symptom of "context poisoning." If your RAG system retrieves three correct documents and two irrelevant ones, the LLM might try to merge them into a single, nonsensical answer. This is a design flaw in the filtering stage. To prevent this, you should implement a "threshold" for similarity scores. If a retrieved document doesn't meet a certain confidence level, it shouldn't be sent to the LLM at all. Most systems are built to always return "k" results, even if those results are garbage. That is what leads to the most common errors.

0
SC
Answered on 16-01-2025

Do you think adding a verification step where the LLM checks the answer against the retrieved snippets could reduce these hallucinations?

LA 17-01-2025

Scott, that is called "Self-RAG." It definitely helps, but it increases costs and latency because you are making multiple LLM calls. For many businesses, the trade-off in speed isn't worth the extra accuracy, which is why they settle for simpler, "worse" designs.

0
RE
Answered on 18-01-2025

Most people just need better prompts. Telling the AI "don't answer if you don't find it in the text" solves a lot of these problems.

JE 19-01-2025

Prompt engineering is a huge part of it, Rebecca. A strict system instruction can act as a final guardrail against those retrieval errors.

Share your thoughts

Your email address will not be published. Required fields are marked (*)

Professional Counselling Session

Still have questions?
Schedule a free counselling session

Our experts are ready to help you with any questions about courses, admissions, or career paths. Get personalized guidance from industry professionals.

Request a Call Back

Search Online

We Accept

We Accept

Follow Us

"PMI®", "PMBOK®", "PMP®", "CAPM®" and "PMI-ACP®" are registered marks of the Project Management Institute, Inc. | "CSM", "CST" are Registered Trade Marks of The Scrum Alliance, USA. | COBIT® is a trademark of ISACA® registered in the United States and other countries.

Book Free Session