PulseAugur
EN
LIVE 11:08:08

AI models show citation monoculture, favoring same papers

By PulseAugur Editorial · [2 sources] ·

A new study reveals that current language models exhibit a significant citation monoculture, meaning they tend to cite the same narrow subset of papers even when presented with a diverse range of options. This phenomenon persists even when the models are provided with real papers and their abstracts, and the citations themselves are accurate. The research suggests that this shared preference map, driven by paper content, is a key factor, indicating that simply mixing vendors or improving retrieval mechanisms is insufficient to broaden AI-generated citations. AI

IMPACT This research highlights a potential bias in AI-driven research discovery, impacting how scientific attention is distributed and potentially limiting exposure to novel or niche findings.

RANK_REASON The cluster is based on an academic paper analyzing the behavior of language models.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

AI models show citation monoculture, favoring same papers

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
The cluster is based on an academic paper analyzing the behavior of language models.
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
49 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Sina Alemohammad, Denghui Zhang, Bolong Tang, Anthony Qin, Gengchen Mai, Ahmed Abbasi, Richard Baraniuk, Zhangyang Wang ·

    When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models

    arXiv:2608.19230v1 Announce Type: cross Abstract: As language models move from drafting prose to running literature-search agents with tool calls, fabricated references are becoming easier to catch and constrain. The harder failure begins after every candidate is real: different …

  2. dev.to — LLM tag TIER_1 English(EN) · Ethan Walker ·

    How Publishers Track Citations in Perplexity and AI Overviews

    <p><a class="article-body-image-wrapper" href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2F9g3skqr68vehadmax8qu.png"><img alt="Cover Image" hei…

RELATED ENTITIES

RELATED TOPICS