Chunking
Splitting source documents into passages small enough to retrieve precisely and embed meaningfully. Chunk too large and the embedding averages several ideas into mush. Chunk too small and a passage loses the context that made it answerable.
Why exams ask this
Exams ask this as a tradeoff question, never as a definition. The answer is almost always about overlap and semantic boundaries rather than a fixed token count.
Relevant to
Related concepts
Resources
No resources linked to this concept yet.