Glossary
The AI reading glossary.
Plain-English definitions of the terms behind trustworthy document AI — what they mean, and why they matter for reading without hallucinations.
AI hallucinationWhen an AI model states something false or unsupported as if it were fact. In document AI, the fix is source-grounding — answering only from retrieved passages and citing them.CitationA pointer from a statement to the source that supports it. In AI, a citation links a generated claim to the exact passage it came from — so the claim can be verified, not just trusted.Optical character recognition (OCR)OCR turns images of text — scanned PDFs, photos, screenshots — into machine-readable, searchable text so software can read, search and cite the words inside them.Retrieval-augmented generation (RAG)A technique where an AI retrieves relevant passages from a source first, then generates an answer grounded in them — reducing hallucination and enabling exact citations.Scroll-to-source citationA citation that doubles as a live pointer: clicking it scrolls to and highlights the exact passage in the original document, turning verification into a single click.Semantic searchSearching by meaning rather than exact keywords, using vector embeddings to match a query against passages that say the same thing in different words.Source-groundingConstraining an AI answer to specific retrieved source text and attaching a citation to each claim, rather than answering from the model's own memory.Vector embeddingA numeric representation of text that captures its meaning, so passages with similar meanings sit close together in space. Embeddings power semantic search and retrieval for AI.