125Your summarizer invents facts that were never in the source article. How do you measure and fix it?▼mediumOpenAIGoogleAnthropic◆ premiumSummarization is the one task where the model was handed everything it needed and still made something up. The signal is separating intrinsic from extrinsic hallucination, knowing why ROUGE cannot see either, and gating on entailment before you ship.Open full answer →
70How do you measure faithfulness (hallucination rate) in a RAG system, and what makes it hard to score?▼mediumAnthropicCohereDatabricks1 replies◆ premiumAn answer can be correct yet still unfaithful, asserting things the retrieved context never said. The signal is scoring faithfulness against the context, not against truth, and knowing why LLM-judge faithfulness scores drift.Open full answer →
141Detect hallucinations in an answer by extracting claims and checking entailment against the sources.▼hardOpenAIAnthropicGlean◆ premiumAsking a model 'is this answer hallucinated?' barely beats a coin flip. This is the build: claim extraction, a judge forbidden from using world knowledge, a denominator that excludes hedges, and one model call per claim, which decides where the check can run at all.Open full answer →
