Why Telling an LLM to Be Careful Doesn't Work: Penalty Prompts Had a 0% Abstention Rate
Ten reproducible experiments on Gemma 2, 3 and 4 with Ollama. Code included. Every developer working with Large Language Models has tried some variation of this prompt: "Answer the question. If you are not completely sure, say 'I don't know'. Do not guess. Accuracy is critical." We write it in syst…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-08 03:31 · DEV Community — Machine Learning
Why Telling an LLM to Be Careful Doesn't Work: Penalty Prompts Had a 0% Abstention Rate