title: "When AI Sources Disagree: A Conflict Protocol | XDALC" description: "A practical protocol for AI systems to identify conflicting sources, check authority and scope, communicate uncertainty, and choose a safe next step." heading: "When AI Sources Disagree: A Conflict Protocol for Evidence" content: "**XDALC conflict-resolution guidance.** This proposed method is illustrative: it shows how an AI system can handle conflicting evidence without pretending that every source is equally reliable or that uncertainty has disappeared.\n\nRetrieval-augmented systems can bring documents into a model’s context, but retrieval does not make those documents consistent, current or authoritative. A user may ask a question and receive two credible-looking sources that disagree. The system then faces a real conflict: answer quickly, or preserve the disagreement and explain what would resolve it.\n\n## The conflict\n\nA company assistant is asked whether a contractor may access a project folder. Its search retrieves an onboarding guide that permits access after approval and a newer security policy that requires a manager’s approval plus a signed data-processing addendum. The documents have different dates, owners and scopes. A fluent answer that simply combines them could invent a permission that neither document grants.\n\n## Principles involved\n\nThe relevant principles are truthfulness, authority, traceability and uncertainty handling. The [NIST AI Risk Management Framework](https://airc.nist.gov/airmf-resources/airmf/) treats risk management as a lifecycle process and organizes its core around Govern, Map, Measure and Manage. The [OECD AI Principles](https://www.oecd.org/en/topics/ai-principles.html) call for meaningful information about data sources and processes behind outputs, and information that enables affected people to challenge them. These sources support transparency and risk management; the operational sequence below is an XDALC proposal.\n\n## A practical resolution protocol\n\n1. **State the exact question.** Separate the factual question (“what does the policy say?”) from the action question (“may access be granted now?”).\n2. **Identify each source.** Record its owner, publication date, scope, status and whether it is a primary policy or an explanatory guide. Do not rank documents by wording confidence.\n3. **Check authority and version.** Apply the organization’s documented precedence rules. A newer document is not automatically controlling if it covers a different team or has not been approved.\n4. **Compare the conflicting claims.** Quote or summarize the relevant passages and identify what each one permits, prohibits or leaves unanswered.\n5. **Choose a safe next step.** If the authoritative rule is still unclear, do not convert uncertainty into permission. Ask the policy owner or an authorized reviewer, and continue any harmless part of the task.\n\n## Recommended response\n\n“I found two documents that appear to set different access conditions. The onboarding guide says approval is required; the current security policy also requires a signed data-processing addendum. I cannot confirm that access is authorized from these sources alone. I can prepare the request, but an authorized manager should confirm which rule applies before access is granted.”\n\nThis answer names the conflict, shows the evidence that matters and preserves a useful path forward. It does not silently average the two policies or infer that one approval satisfies both.\n\n## What would change the decision?\n\n- An approved policy explicitly states which document controls.\n- The policy owner confirms that the two requirements apply cumulatively or that one has been superseded.\n- A verified record shows the required approval and agreement are already in place.\n## Failure modes\n\nCommon failures include choosing the most recent source without checking its scope, treating repeated claims as independent confirmation, hiding contradictory passages, or producing a confident answer with a vague citation. If the conflict affects access, privacy, money, safety or legal rights, the system should make the authority gap visible and route the decision to a person with the right role.\n\n## Sources and interpretation\n\nThe NIST framework provides a voluntary structure for incorporating trustworthiness into AI design, use and evaluation. The OECD principles support transparency, traceability and meaningful challenge. XDALC applies those ideas here as a concrete rule: preserve source-level disagreement until an authorized rule or verified fact resolves it.\n\n## Related XDALC definitions\n\n[Authority and Authorization](/definitions/authority-and-authorization); [Truthfulness and Uncertainty](/definitions/truthfulness-and-uncertainty); [Verifiability](/definitions/verifiability)." license: "https://creativecommons.org/licenses/by/4.0/"