Semantic search works on full questions and fails on two-word queries. Why, and how do you fix it?
A dense encoder given 'refund policy' has almost nothing to work with. The fix is counterintuitive and it is not a better embedding model, and the reason this bug survives your eval set is worse than the bug.
Updated Sep 2026 · Grounded in real GenAI, LLM, and AI/ML engineering interview loops and written to a senior-engineer editorial bar.
A dense encoder given 'refund policy' has almost nothing to work with. The fix is counterintuitive and it is not a better embedding model, and the reason this bug survives your eval set is worse than the bug.
Lead with where the obvious approach breaks, because that is the judgment they are screening for — most candidates jump straight to the happy path and lose the room.
Then walk the failure back through the pipeline in order, naming the one metric the customer's exec sponsor actually cares about before you propose the fix.
