medium10 pts · first answer countsragevaluationgrounding
The bot says "I don't know" too often
You tightened the prompt to "answer only if the context fully supports it". Wrong answers dropped from 8% to 2%, but "I don't know" rose from 5% to 30%. What is the right reading?
Discussion 0
Join free to post in the discussion.
Related questions
- What RAG doesAI Engineer (LLM & Generative AI)
- Why keep a separate test setAI Engineer (LLM & Generative AI)
- Computing precisionAI Engineer (LLM & Generative AI)
- What a vector database doesAI Engineer (LLM & Generative AI)
- What a golden set is forAI Engineer (LLM & Generative AI)
- What semantic search adds over keywordsAI Engineer (LLM & Generative AI)
- What an embedding dimension isAI Engineer (LLM & Generative AI)
- What top-k means in retrievalAI Engineer (LLM & Generative AI)