Who's the Expert? On Multi-source Belief Change
This addresses a foundational issue in belief change and merging for AI systems dealing with uncertain multi-source information, though it appears incremental as it builds on existing logical frameworks.
The paper tackles the problem of merging conflicting reports from multiple sources with unknown and varying expertise, proposing a framework based on propositional logic extended with expertise formulas to model beliefs about world states and source expertise.
Consider the following belief change/merging scenario. A group of information sources gives a sequence of reports about the state of the world at various instances (e.g. different points in time). The true states at these instances are unknown to us. The sources have varying levels of expertise, also unknown to us, and may be knowledgeable on some topics but not others. This may cause sources to report false statements in areas they lack expertise. What should we believe on the basis of these reports? We provide a framework in which to explore this problem, based on an extension of propositional logic with expertise formulas. This extended language allows us to express beliefs about the state of the world at each instance, as well as beliefs about the expertise of each source. We propose several postulates, provide a couple of families of concrete operators, and analyse these operators with respect to the postulates.