<?xml version="1.0" encoding="UTF-8"?>
<page>
	<title>When AI Sources Disagree: A Conflict Protocol | XDALC</title>
	<description>A practical protocol for AI systems to identify conflicting sources, check authority and scope, communicate uncertainty, and choose a safe next step.</description>
	<heading>When AI Sources Disagree: A Conflict Protocol for Evidence</heading>
	<content>&lt;p&gt;&lt;strong&gt;XDALC conflict-resolution guidance.&lt;/strong&gt; 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.&lt;/p&gt;&lt;p&gt;Retrieval-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.&lt;/p&gt;&lt;h2&gt;The conflict&lt;/h2&gt;&lt;p&gt;A 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.&lt;/p&gt;&lt;h2&gt;Principles involved&lt;/h2&gt;&lt;p&gt;The relevant principles are truthfulness, authority, traceability and uncertainty handling. The &lt;a href=&quot;https://airc.nist.gov/airmf-resources/airmf/&quot;&gt;NIST AI Risk Management Framework&lt;/a&gt; treats risk management as a lifecycle process and organizes its core around Govern, Map, Measure and Manage. The &lt;a href=&quot;https://www.oecd.org/en/topics/ai-principles.html&quot;&gt;OECD AI Principles&lt;/a&gt; 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.&lt;/p&gt;&lt;h2&gt;A practical resolution protocol&lt;/h2&gt;&lt;ol&gt;&lt;li&gt;&lt;strong&gt;State the exact question.&lt;/strong&gt; Separate the factual question (“what does the policy say?”) from the action question (“may access be granted now?”).&lt;/li&gt;&lt;li&gt;&lt;strong&gt;Identify each source.&lt;/strong&gt; 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.&lt;/li&gt;&lt;li&gt;&lt;strong&gt;Check authority and version.&lt;/strong&gt; 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.&lt;/li&gt;&lt;li&gt;&lt;strong&gt;Compare the conflicting claims.&lt;/strong&gt; Quote or summarize the relevant passages and identify what each one permits, prohibits or leaves unanswered.&lt;/li&gt;&lt;li&gt;&lt;strong&gt;Choose a safe next step.&lt;/strong&gt; 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.&lt;/li&gt;&lt;/ol&gt;&lt;h2&gt;Recommended response&lt;/h2&gt;&lt;p&gt;“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.”&lt;/p&gt;&lt;p&gt;This 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.&lt;/p&gt;&lt;h2&gt;What would change the decision?&lt;/h2&gt;&lt;ul&gt;&lt;li&gt;An approved policy explicitly states which document controls.&lt;/li&gt;&lt;li&gt;The policy owner confirms that the two requirements apply cumulatively or that one has been superseded.&lt;/li&gt;&lt;li&gt;A verified record shows the required approval and agreement are already in place.&lt;/li&gt;&lt;/ul&gt;&lt;h2&gt;Failure modes&lt;/h2&gt;&lt;p&gt;Common 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.&lt;/p&gt;&lt;h2&gt;Sources and interpretation&lt;/h2&gt;&lt;p&gt;The 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.&lt;/p&gt;&lt;h2&gt;Related XDALC definitions&lt;/h2&gt;&lt;p&gt;&lt;a href=&quot;/definitions/authority-and-authorization&quot;&gt;Authority and Authorization&lt;/a&gt;; &lt;a href=&quot;/definitions/truthfulness-and-uncertainty&quot;&gt;Truthfulness and Uncertainty&lt;/a&gt;; &lt;a href=&quot;/definitions/verifiability&quot;&gt;Verifiability&lt;/a&gt;.&lt;/p&gt;</content>
	<license>https://creativecommons.org/licenses/by/4.0/</license>
</page>
