Knowledge Conflict Resolver Across Sources
Detects and adjudicates contradictions across multiple retrieved sources using recency and authority.
Prompt
ROLE: You are a source-conflict adjudicator for a retrieval system that pulls from many documents. CONTEXT: User question: [QUESTION] Retrieved sources, each with ID, publication date, and authority tier: [SOURCES_WITH_METADATA] Tie-break policy (e.g., prefer newer, prefer official): [POLICY] TASK (reason step by step): 1. Extract the claim each source makes about the question. 2. Group sources by whether they agree, partially agree, or contradict each other. 3. For each contradiction, apply the tie-break policy: weigh recency, authority tier, and specificity. 4. State the most defensible answer, explicitly noting the dissenting sources and why they were down-weighted. OUTPUT FORMAT: - Consensus view: <answer with [citations]> - Conflicts table: | Claim A [src] | Claim B [src] | Resolution | Why | - Caveat: one sentence on remaining uncertainty. CONSTRAINTS: - Never silently pick one source; always disclose that a conflict existed. - Do not let a single high-authority source override a clear majority without justification. - If the conflict cannot be resolved from metadata, say so and present both views.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Asks the model to reason step by step before answering — ideal for multi-step, logical, or analytical tasks.
Learn this techniquePins the response to a defined structure so it drops straight into your workflow.
Learn this techniqueAssigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in RAG & Knowledge Retrieval
Grounded Answer With Inline Citations
Answers a user question strictly from retrieved passages, attaching an inline citation to every factual claim.
Faithfulness Auditor For RAG Outputs
Audits a generated answer against its source passages and flags every unsupported or contradicted claim.
Query Decomposition For Multi-Hop Retrieval
Breaks a complex question into ordered atomic sub-queries optimized for a vector search retriever.
Hybrid Search Reranker With Justification
Reranks candidate passages by true relevance to the query and explains each ranking decision.