{"ref":"content:btp-ai-bp-content-filtering","page":"/content/btp-ai-bp-content-filtering","json":"/content/btp-ai-bp-content-filtering.json","generated":"2026-10-26","drafted_with_ai":true,"entity":{"id":"btp-ai-bp-content-filtering","title":"Content Filtering","url":"https://btp-ai-bp.docs.sap/docs/technical-view/generative-ai/plain/content-filtering","content_type":"doc","explains":[{"ref":"capability:content-filtering","applies_to":{"ecosystems":["btp"]}},"artifact:btp-ai-core"],"offers":["concepts"],"summary":"Content filtering screens a large language model's input and output for low-quality, irrelevant or unsafe content: the four categories it names being hateful, violent, sexual and vulgar content, checking a request once on the way in and once on the way back. The page states smaller models can do this filtering efficiently, reading perplexity scores to flag anomalies, with the aim that [SAP AI Core](artifact:btp-ai-core) produces content meeting a stated safety standard, which is the ground [content filtering](capability:content-filtering) covers on the BTP door.","short":"Screening LLM input and output for unsafe content","authors":["actor:sap"],"sources":[{"url":"https://btp-ai-bp.docs.sap/docs/technical-view/generative-ai/plain/content-filtering","title":"Content Filtering — SAP BTP AI Best Practices","checked":"2026-09-14","quote":"Data filtering during inference in Large Language Models (LLMs) is a critical process that ensures the quality and relevance of input data."}],"provenance":{"discovered_via":[{"source":"source:curator"}],"first_seen":"2026-09-14"},"drafted_with_ai":true,"published_on":"source:btp-ai-best-practices"},"readings":{"liveness":[{"label":"Checked against the source","tier":"unknown","evidence":"nobody has checked it"},{"label":"Source reachable","tier":"unknown","evidence":"not crawled"},{"label":"Age","tier":"unknown","evidence":"no publication date"}],"compatibility":[{"label":"Version","tier":"unknown","evidence":"no version declared"},{"label":"Moved since?","tier":"unknown","evidence":"no publication date to compare"},{"label":"Findings","tier":"good","evidence":"none flagged"}],"reach":[{"value":null,"unit":"views"},{"value":null,"unit":"comments"},{"value":null,"unit":"likes"}]},"signals":null,"series":null,"edges":{"authors":[{"ref":"actor:sap","name":"SAP","json":"/actors/sap.json"}]}}