The paper introduces CiteResolve, a benchmark of 423 real-world hallucinated citations annotated for source recoverability, and CiteAnchor, a source-aware grounding framework that adapts retrieval and field-level verification to each source type. CiteAnchor determines citation validity and whether a unique source can be recovered, achieving 0.841 F1 on an existing detection benchmark and 74.7% end-to-end success on CiteResolve, outperforming baselines by significant margins. The authors provide code and data at their GitHub repository.
arXiv:2609.14248v1 Announce Type: cross Abstract: Faithful citation attribution begins with identifying the intended source for a scientific claim. We study this source-identification capability thro...
arXiv:2607. 00738v1 Announce Type: cross Abstract: Large language models can generate polished scientific text that includes unsupported claims, allowing hallucinations to enter the archival record.
CiteVQA is a benchmark that evaluates multimodal large language models on both answering document questions and providing element‑level bounding‑box citations for the evidence used. It contains 1,897 questions across 711 PDFs in seven domains and two languages, with ground‑truth citations generated via an automated pipeline and strict quality control. The evaluation metric, Strict Attributed Accuracy (SAA), rewards a prediction only when both the answer and the cited region are correct, revealing widespread attribution hallucination in current models.
AtomCite is an agentic framework that verifies and corrects page‑level citations in multi‑page documents by parsing answers into claims, checking each claim against the cited page image, and applying a deterministic repair policy. The authors introduce DocCite, the first benchmark for this task, built on MP‑DocVQA and DUDE, containing 928 injected instances and 1,909 verified natural errors. Across Gemini, Claude, and GPT models, AtomCite achieves about 93% verification accuracy and improves citation precision from 34% to 87‑90%, while also enhancing hallucination detection in open‑source models.
arXiv:2607. 22706v1 Announce Type: new Abstract: This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrieval and the absence of source verification.
arXiv:2606. 18385v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs.
arXiv:2609.14245v1 Announce Type: cross Abstract: Context compression reduces generator input in retrieval-augmented generation, but answer quality alone does not characterize citation attribution. W...
CITECHOICE is a causal audit that examines how the presentation of documents in an agentic search engine redistributes citation credit. Using 129 everyday‑query transcripts, the study compares structured versus prose renderings of the same source while keeping all other transcript elements fixed. The results show that structured rendering increases the target’s citation count by about half a citation per answer without adding total citations or diminishing competitors’ credit, while also revealing that rank position has a larger effect on citation rates than presentation order alone.
arXiv:2506.17585v4 Announce Type: replace Abstract: Large language models can answer questions correctly and still hallucinate their citations. Most citation systems address this by retrieving docume...
arXiv:2607.18360v2 Announce Type: replace-cross Abstract: GPTZero found 53 NeurIPS 2025 accepted papers with hallucinated citations, and venues now screen submissions with automated reference checker...
arXiv:2609.10293v1 Announce Type: new Abstract: In high-stakes domains such as legal practice, a language-model answer is only useful to the extent that a reader can verify each claim against the sou...
The paper introduces REASONS, a benchmark comprising 12,723 sentence-level citation instances across 12 arXiv subject categories, to evaluate scientific citation attribution by large language models. It proposes a dual-metric framework—Abstention Rate (AR) and Hallucination Rate (HR)—to assess the trade-off between reliability and responsiveness. Experiments on proprietary and open-source LLMs under various prompting and retrieval settings show that advanced Retrieval-Augmented Generation (RAG) reduces hallucinations but may increase abstention, while retrieval-augmented variants often maintain near-zero abstention. Human evaluation reveals a high ratio of factual hallucinations to acceptable paraphrases, underscoring the need for systems that can appropriately abstain under uncertainty.