Skip to content
All tags

#retrieval-augmented-generation

2 posts
ai deep-dive

Self-RAG: Teaching the Model to Decide When to Retrieve

Self-RAG trains four reflection tokens (Retrieve / IsREL / IsSUP / IsUSE) into an LLM, letting it decide on-the-fly whether to retrieve, whether results are relevant, and whether its own output is grounded. ICLR 2024 Oral (top 1%), the 7B model beats ChatGPT and Llama2-chat + RAG on multiple QA benchmarks. The catch: it requires fine-tuning—no API-only models.

#self-rag#adaptive-retrieval#reflection-tokens#rag#retrieval-augmented-generation
ai deep-dive 認識 AI 模型

Fine-tuning vs RAG: When to Teach the Model vs When to Look Things Up

Data changes often and you need citations → RAG. Need consistent style or want to run on a small device → fine-tuning. In practice, many production systems use both: fine-tune a small model that speaks your domain language, then use RAG to supply up-to-date facts.

#fine-tuning#rag#retrieval-augmented-generation#llm#ai-model#vector-database