Metraipolis › archive › dc_589166c0d673
Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation — arXiv:2609.01432
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01432
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:41:49.636Z
- SHA-256 of the archived text
2ff123a40830d35efbab6c483294dc0e2498366cb483444b4eb8cdd6d15c831d- Stable URL of this page
https://metraipolis.com/documento/dc_589166c0d673
How to cite
Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation — arXiv:2609.01432 — arXiv (en), https://arxiv.org/abs/2609.01432 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_589166c0d673 (Metraipolis archive dc_589166c0d673, sha256 2ff123a40830d35efbab6c483294dc0e2498366cb483444b4eb8cdd6d15c831d)
BibTeX
@misc{dc589166c0d673,
title = {Citing Less Critically: LLMs Reshape the Rhetoric and Reach of Scientific Citation — arXiv:2609.01432},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01432},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_589166c0d673; sha256 2ff123a40830d35efbab6c483294dc0e2498366cb483444b4eb8cdd6d15c831d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01432. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scientific citations carry rhetorical intent. Scholars may cite prior work positively (supporting), negatively (contrasting), or neutrally (mentioning). As large language models (LLMs) increasingly assist scientific writing, whether they reproduce citations with the same rhetorical intent as humans remains unclear. We introduce a masked-citation task to compare human and LLM-generated citation behavior. For each citation context, an LLM generates a replacement citation sentence, producing a counterfactual corpus directly comparable to human citation. We analyze what, whom, and how models cite, using an LLM-as-a-judge to classify citation intent and a 20-million-edge coauthorship network to measure social distance between cited authors. Across six popular LLMs and 1,746 top NLP conference papers (63k+ contexts, 132k+ citations), three patterns emerge: (1) Compared with human citation, LLMs cite significantly less critically; (2) LLMs over-cite popular and older papers, a tendency amplified for contrasting citations where human writing more often draws on recent, niche work; (3) Whereas humans often cite within their close social network, especially for supporting citations, LLMs tend to draw on more socially distant authors. Together, these differences are double-edged: LLM citation reaches beyond a scholar's close collaborators while being less critical and amplifying visibility bias, reshaping the rhetoric and reach of scientific citation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CL). Categorie arXiv: Digital Libraries (cs.DL) ; Computation and Language (cs.CL); Computers and Society (cs.CY); Social and Information Networks (cs.SI). Pagina del lavoro: https://arxiv.org/abs/2609.01432 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:33:38.901Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).