In this case, what's really needed is high-level labor (organization, and maybe programming), and not low-level labor (typing in the damn references by hand). I guess it's easier to get volunteers to do the latter, and the "high-level" volunteers are mostly editors and wiki-policy wonks, not thinking about appropriate data structures and implementation.
It is striking how little Wikipedia has advanced technically since it started, compared with its enormous growth of content.
I think the enormous growth of content (and usage) is exactly why Wikipedia hasn't advanced much technically. In its early years it was a total shoestring operation, mainly focused on keeping the site up under incredible traffic. Just surviving that is a titanic victory.
However, that victory came at a cost: the software fell way behind. The community picked up the slack, making a fantastic reference site despite the handicaps. But many of the ways they did that (e.g., duplicating references all over the place) make improving the software even harder.
Now that Wikimedia Foundation staffing is starting to catch up, I'm sure some of these things will get better. But it's definitely going to take a while.
It is striking how little Wikipedia has advanced technically since it started, compared with its enormous growth of content.