mallen-2023-entity-popularity-via-wikipedia-pageviews

IN premise — summaries/2026/08/24/mallen-2023-when-not-to-trust-s2-related-work.md

Created 2026-08-25T02:58:10+00:00

Mallen et al. 2023 measures subject entity popularity using Wikipedia monthly page views as a proxy for web discussion frequency, rather than counting entity occurrences in pretraining corpora.

Summary

Mallen et al. 2023 anchors entity popularity in live public interest, specifically how many people are reading a Wikipedia article in a given month, rather than in how often the name shows up in training text. This matters because it ties the system's sense of what is well-known to what people are actually engaging with right now, instead of the historical frequency of a string in a pretraining corpus.