How LLMs Cite and Why It Matters: A Cross-Model Audit of Reference Fabrication in AI-Assisted Academic Writing and Methods to Detect Phantom Citations

2026-02-07 · MZ Naser arxiv

Large language models (LLMs) have been noted to fabricate scholarly citations, yet the scope of this behavior across providers, domains, and prompting conditions remains poorly quantified. We present one of the largest citation hallucination audits to date, in which 10 commercially deployed LLMs were prompted across four academic domains, generating 69,557 citation instances verified against three scholarly databases (namely, CrossRef, OpenAlex, and Semantic Scholar). Our results show that the observed hallucination rates span a fivefold range (between 11.4% and 56.8%) and are strongly shaped by model, domain, and prompt framing. Our results also show that no model spontaneously generates citations when unprompted, which seems to establish hallucination as prompt-induced rather than intrinsic. We identify two practical filters: 1) multi-model consensus (with more than 3 LLMs citing the same work yields 95.6% accuracy, a 5.8-fold improvement), and 2) within-prompt repetition (with more than 2 replications yields 88.9% accuracy). In addition, we present findings on generational model tracking, which reveal that improvements are not guaranteed when deploying newer LLMs, and on capacity scaling, which appears to reduce hallucination within model families. Finally, a lightweight classifier trained solely on bibliographic string features is developed to classify hallucinated citations from verified citations, achieving AUC 0.876 in cross-validation and 0.834 in LOMO generalization (without querying any external database). This classifier offers a pre-screening tool deployable at inference time.

📄 PDF Abstract BibTeX arXiv:2603.03299

Code (0)

등록된 구현이 없습니다.

CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era

2026-02-26 · Kaiwen Shi, Weixiang Sun, Zheyuan Zhang, Lichao Sun 외 arxiv

Scientific research relies on citation integrity, yet large language models (LLMs) have introduced a critical risk: fabricated references that appear plausible but correspond to no real publications. As manual verificati…

CitePrism: Human-in-the-Loop AI for Citation Auditing and Editorial Integrity

2026-05-15 · Gowrika Mahesh, Budanur Madappa Darshan Gowda, Kavana Gopladevarahalli Papegowda, Prajwal Basavaraj 외 arxiv

Editors and reviewers are expected to ensure that manuscripts cite relevant, accurate, current, and ethically appropriate literature, yet manuscript-level citation auditing remains largely manual, fragmented, and difficu…

Semantic Similarity

DrugClaw and DrugAudit: A Primary-Source-Grounded Agent and Authority-Aware Benchmark for Drug-Information Question Answering

2026-05-31 · Qing Wang, Bo Li, Jialu Liang, Daling Shi 외 arxiv

Drug-information question answering is a high-stakes setting where hallucinated facts can mislead clinical decision-making and the provenance of each cited fact matters as much as the fact itself. We present DrugClaw, a …

Question Answering

What Matters to You? Towards Visual Representation Alignment for Robot Learning

2023-10-11 · Ran Tian, Chenfeng Xu, Masayoshi Tomizuka, Jitendra Malik 외

When operating in service of people, robots need to optimize rewards aligned with end-user preferences. Since robots will rely on raw perceptual inputs like RGB images, their rewards will inevitably use visual representa…

Zero-shot Generalization

False Confidence: Automated Labels Confound Fairness Audits in Cervical Spine Segmentation

2026-07-08 · Linus Juni, Aasa Feragen, Aditya Parikh arxiv

Automated segmentation of cervical-spine MRI is increasingly used in clinical workflows, yet no fairness audit exists for this anatomy. We show that auditing these segmentation tasks is complicated by a common property o…