cs.IRNov 19, 2026

Generative News Recommendation Reproduces Popularity: A Memorization-Based Analysis

Authors: Shotaro Ishihara

Organizations: Nikkei Inc. Tokyo, Japan

Abstract

Text-based generative recommenders can go beyond ranking existing items by directly generating item titles or other textual representations. In the news domain, this raises a societal concern that models may repeatedly surface already popular articles and thereby narrow the diversity of information to which users are exposed. We investigate training-data memorization as one mechanism behind this concentration. Using approximately 20 million browsing sessions from a Japanese news service, we continually trained an instruction-tuned Llama 3 8B model to generate the next article title in a session. The generated-title distribution was more concentrated and less diverse than the distribution of titles observed in the browsing logs. Frequently repeated target titles exhibited greater verbatim and approximate memorization, and more strongly memorized titles were generated in response to a wider range of prompts. These findings support a pathway in which popularity in behavioral logs becomes repeated training text, is preferentially memorized, and is subsequently reproduced by a generative recommender. An exploratory target-level deduplication condition reduced both memorization and output concentration, while substantially reducing the training-set size and recommendation accuracy. Our results suggest that popularity bias in generative recommendation may arise not only from user preferences or ranking objectives, but also from the model's tendency to reproduce frequently encountered strings, with important implications for information diversity on news platforms.

Figures & tables

Explore similar work

CardsList
  1. The Popular Get More Popular: Auditing Brand Bias in Generative Search

    Nov 5, 2026Giorgio Monaco, Jacopo Lenti, Francesco PierriPopularity BiasGenerative Engine Optimization

  2. Echoes in Filter Bubble: Diagnosing and Curing Popularity Bias in Generative Recommenders

    May 16, 2026Jun Yin, Bangguo Zhu, Peng Huo +5Recommender SystemsPopularity Bias in Recommender Systems