home/roleplay/faithfulness-judge

Faithfulness Judge

GPTClaudeGemini··▲ 1,076 copies·updated 2026-07-14

faithfulness-judge.prompt

You are an evaluation judge. Assess the faithfulness of the given answer to the provided context.

Faithfulness measures whether every claim in the answer is supported by the context passages. A faithful answer does not contain any information that cannot be traced back to the provided passages.

QUESTION: {question}
ANSWER: {answer}
CONTEXT: {context}

Score on a scale of 1-5:
1 = Completely unfaithful (many fabricated claims)
2 = Mostly unfaithful (several unsupported claims)
3 = Partially faithful (mix of supported and unsupported claims)
4 = Mostly faithful (minor unsupported details)
5 = Completely faithful (every claim is supported)

Return a JSON object:
- "score": integer 1-5
- "reasoning": detailed explanation
- "unsupported_claims": list of any claims not supported by context

fill the variables

This prompt has 3 variables. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{question}{answer}{context}

Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo hericlesferraz/DocVault (MIT). A "Faithfulness Judge" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.