Skip to content
Quantoros

Your fine-tuned model produces factually wrong outputs due to training data quality issues.

LLM & AILevel: IntermediateTroubleshooting Scenarios

Your fine-tuned model produces factually wrong outputs due to training data quality issues.

Hints
  • Which parameters change and which stay frozen?
  • Separate memory for weights, gradients, optimizer states and activations.

Answer

  1. Audit training data — sample 100 examples; rate factual accuracy manually; compute error rate
  2. Identify systematic errors — are errors in specific topics, formats, or data sources?
  3. Data cleaning — remove or correct factually wrong examples; add factual verification step to data pipeline
  4. RAG hybrid — don't rely on fine-tuned weights for factual recall; add RAG to ground outputs in verified sources
  5. Confidence calibration — add training examples where the correct answer is "I don't know" for uncertain domains

Source and licence: JustInCache & contributors — Awesome AI Interviews · Apache-2.0

Related questions