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

• URL: http://arxiv.org/abs/2608.19230v1
• Date: Mon, 03 Aug 2026 14:27:46 GMT
• Title: When AI Writes, Who Gets Cited? Evidence of Citation Monoculture Across Language Models
• Abstract summary: We show that different models may still select the same narrow subset, producing citation monoculture without any single citation being wrong.<n>Eleven models from three vendors choose at most ten papers from uniformly random panels of thirty, with real titles and abstracts but fabricated authors, reassigned years, and hidden venues and citation counts.
• Score: 45.91367912142692
• License: http://creativecommons.org/licenses/by/4.0/
• 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 models may still select the same narrow subset, producing citation monoculture without any single citation being wrong. We isolate this effect on 120 real papers. Eleven models from three vendors choose at most ten papers from uniformly random panels of thirty, with real titles and abstracts but fabricated authors, reassigned years, and hidden venues and citation counts. Each run is compared with indifferent selection on the same panel and realized budget. All eleven models concentrate sharply: the top decile receives 23.3-30.2% of citations against 15.6% under the null, one component explains 68-73% of variation across their preference maps, and cross-vendor agreement nearly matches within-vendor agreement. Formalizing the task as fixed-budget subset selection, we turn these patterns into identifiable mechanisms: an exchangeability bound rejects a mapless selector for every model, a spectral decomposition explains why the best cross-fitted mixture still retains 55% of the excess, and a rarity theorem predicts the recursive competition effect we verify within panels. Controlled paraphrase, content-slot crossover, and design resampling attribute about 90% of GPT-5 mini's map variance to paper content. Eight domain experts selecting from the same blinded panels under the same cap show no comparable shared preference, while model concentration persists in selection-only mode. Even when every reference is real and every paper is equally visible, current language models impose a common content-level filter on scientific attention. Equalizing retrieval or mixing vendors is therefore insufficient; the shared preference map itself must be changed.

Related papers

• Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning Failure [51.736723807086385]
  Population-marginal agreement is evidence about an elicitation contract and an estimand obtainable without simulated respondents, not evidence of individual simulation.<n>On nine aligned model-battery pairs, a no-persona population-prevalence query averages 6.27 MAE versus 12.39 for committed panels and wins all nine comparisons.
  arXiv  Detail & Related papers  (2026-09-07T10:22:22Z)
• Beyond Similarity: Grounded Agentic Extraction and Expert-Adjudicated Evaluation of Intertextuality in Classical Chinese Histories [3.694051864521789]
  We recast fine-grained intertextuality extraction as an agentic task in which a large language model reads two text units in full.<n>We validate the approach on an exhaustive comparison of the Analects with the Book of Han, where three domain experts adjudicate a pooled multi-model candidate set into a benchmark of 2,533 intertextual pairs.
  arXiv  Detail & Related papers  (2026-07-30T02:34:23Z)
• One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions [0.0]
  API aggregators, resellers, and inference providers consume large language models (LLMs)<n>Existing identification techniques require long generated texts, token-level log-probabilities, adversarially crafted prompts, or the model owner's cooperation.<n>We define a behavioral fingerprint of an LLM as the empirical distribution of its answers to trivial one-word prompts.
  arXiv  Detail & Related papers  (2026-07-11T10:34:17Z)
• Measuring the sensitivity of LLM-based structured extraction to prompt, model, and schema choices in clinical discharge summaries [0.0]
  Large language models are increasingly used for structured extraction from clinical free-text notes.<n>This work measures that sensitivity without human-annotated ground truth, by holding the extraction task fixed and varying one choice at a time.<n>Cross-prompt agreement was measured by Cohen's kappa on ICD-stratified subsets.
  arXiv  Detail & Related papers  (2026-06-04T10:14:12Z)
• FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks [0.0]
  A paraphrase-quality audit of MathCheck detected 4 semantically incorrect paraphrases in 129 groups.<n>Removing them drops GPT-4o from rank 2 to rank 4 and elevates Claude Haiku and DeepSeek V3 above it.
  arXiv  Detail & Related papers  (2026-05-27T18:59:18Z)
• Pando: Do Interpretability Methods Work When Models Won't Explain Themselves? [53.07826484214082]
  We introduce Pando, a model-organism benchmark that breaks this confound via an explanation axis.<n>Pando predicts held-out model decisions from $10$ labeled query-response pairs.<n>When explanations are faithful, black-box elicitation matches or exceeds all white-box methods.
  arXiv  Detail & Related papers  (2026-04-13T06:42:24Z)
• SciClaimEval: Cross-modal Claim Verification in Scientific Papers [16.873180911172838]
  We present SciClaimEval, a new scientific dataset for the claim verification task.<n>SciClaimEval features authentic claims, including refuted ones, directly extracted from published papers.<n>To create refuted claims, we introduce a novel approach that modifies the supporting evidence (figures and tables), rather than altering the claims or relying on large language models (LLMs) to fabricate contradictions.
  arXiv  Detail & Related papers  (2026-02-07T16:58:55Z)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Localized Randomized Smoothing for Collective Robustness Certification [60.83383487495282]
  We propose a more general collective robustness certificate for all types of models. We show that this approach is beneficial for the larger class of softly local models. The certificate is based on our novel localized randomized smoothing approach.
  arXiv  Detail & Related papers  (2022-10-28T14:10:24Z)
• MIDAS at SemEval-2020 Task 10: Emphasis Selection using Label Distribution Learning and Contextual Embeddings [46.973153861604416]
  This paper presents our submission to the SemEval 2020 - Task 10 on emphasis selection in written text. We approach this emphasis selection problem as a sequence labeling task where we represent the underlying text with contextual embedding models. Our best performing architecture is an ensemble of different models, which achieved an overall matching score of 0.783, placing us 15th out of 31 participating teams.
  arXiv  Detail & Related papers  (2020-09-06T00:15:33Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.