Collective argument evaluation as judgement aggregation

A conflicting knowledge base can be seen abstractly as a set of arguments and a binary relation characterising conflict among them. There may be multiple plausible ways to evaluate conflicting arguments. In this paper, we ask: given a set of agents, each with a legitimate subjective evaluation of a set of arguments, how can they reach a collective evaluation of those arguments? After formally defining this problem, we extensively analyse an argument-wise plurality voting rule, showing that it suffers a fundamental limitation. Then we demonstrate, through a general impossibility result, that this limitation is more fundamentally rooted. Finally, we show how this impossibility result can be circumvented by additional domain restrictions.