CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery
Authors: Mengze Hong, Di Jiang, Chen Jason Zhang, Zichang Guo, Yawen Li, Jun Chen, Shaobo Cui, Zhiyang Su
Organizations: Hong Kong Polytechnic University, Hong Kong, China · Beijing University of Posts and Telecommunications, Beijing, China · Independent Researcher, Hong Kong, China · Swiss Federal Technology Institute of Lausanne (EPFL), Lausanne, Switzerland · Hong Kong University of Science and Technology (HKUST), Hong Kong, China
Large language models (LLMs) have created new opportunities to enhance the efficiency of scholarly activities; however, challenges persist in the ethical deployment of AI assistance, including (1) the trustworthiness of AI-generated content, (2) preservation of academic integrity and intellectual property, and (3) protection of information privacy. In this work, we present CiteLLM, a specialized agentic platform designed to enable trustworthy reference discovery for grounding author-drafted claims and statements. The system introduces a novel interaction paradigm by embedding LLM utilities directly within the LaTeX editor environment, ensuring a seamless user experience and no data transmission outside the local system. To guarantee hallucination-free references, we employ dynamic discipline-aware routing to retrieve candidates exclusively from trusted web-based academic repositories, while leveraging LLMs solely for generating context-aware search queries, ranking candidates by relevance, and validating and explaining support through paragraph-level semantic matching and an integrated chatbot. Evaluation results demonstrate the superior performance of the proposed system in returning valid and highly usable references.
Figures & tables
Figure 1. Overview of CiteLLM: trustworthy reference discovery powered by three LLM-based utility agents.
Figure 2. Demonstration of user interface: a full LaTeX editor with embedded reference discovery in four steps: (1) select sentence, (2) one-click citation discovery, (3) reference search process, (4) context-aware chatbot discussion
Figure 3. Example of reference discovery result.
Method
Validity (%)
Precision (%)
Usability (%)
Human
GPT-5
Human
GPT-5
CiteLLM (ours)
100
84.0
87.5
87.5
92.5
Google Scholar
100
64.0
73.5
80.0
85.0
ChatGPT
74
84.5
91.9
30.0
37.5
*Note: Precision for ChatGPT is evaluated among the valid references.
Table 1. Performance comparison of citation discovery methods ( N=40 sentences, top-5 references per sentence).
Figure 4. Comparison of query construction approaches.
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 verification becomes infeasible and existing automated tools remain fragile, we introduce CiteAudit, a comprehensive benchmark and detection framework for hallucinated citations. We design a multi-agent verification pipeline that decomposes citation checking into metadata extraction, memory lookup, web-based retrieval, and final judgment. To evaluate this, we construct a large-scale, human-validated dataset spanning diverse domains and hallucination types. Experiments demonstrate that our framework achieves superior verification performance over state-of-the-art LLMs and commercial baselines. Our work provides the necessary infrastructure to audit citations at scale and safeguard the trustworthiness of scholarly discourse. Code is available at https://github.com/shiiiikw/CiteAudit.
Large language models (LLMs) are increasingly used to generate scientific reports, but they can produce references that appear plausible while containing corrupted metadata or pointing to papers that do not exist. We introduce CiteCheck, a hybrid framework for citation hallucination detection that verifies whether a citation corresponds to a real scholarly work and whether its metadata is faithful to that work. CiteCheck retrieves candidate publications from external scholarly sources, compares the citation against the retrieved candidate using a structured LLM verifier, and maps verifier scores into three labels: Exact, Minor, and Major. We also construct a 982-citation physics benchmark with controlled corruptions that capture both subtle metadata drift and fully fabricated references. On the held-out test set, CiteCheck achieves 88.7 macro-F1 and 88.9% accuracy, outperforming GPT, Claude, and Gemini baselines, including web-search and few-shot variants. These results show that reliable citation verification benefits from combining scholarly retrieval, structured LLM-based comparison, and calibrated decision rules.
LLMs are increasingly used to draft academic text and to support software engineering (SE) evidence synthesis, but they often hallucinate bibliographic references that look legitimate. We study how deployment-motivated prompting constraints affect citation verifiability in a closed-book setting. Using 144 claims (24 in SE&CS) and a deterministic verification pipeline (Crossref + Semantic Scholar), we evaluate two proprietary models (Claude Sonnet, GPT-4o) and two open-weight models (LLaMA3.1-8B, Qwen2.5-14B) across five regimes: Baseline, Temporal (publication-year window), Survey-style breadth, Non-Disclosure policy, and their combination. Across 17,443 generated citations, no model exceeds a citation-level existence rate of 0.475; Temporal and Combo conditions produce the steepest drops while outputs remain format-compliant (well-formed bibliographic fields). Unresolved outcomes dominate (36-61%); a 100-citation audit indicates that a substantial fraction of Unresolved cases are fabricated. Results motivate post-hoc citation verification before LLM outputs enter SE literature reviews or tooling pipelines.
Chen Zhao, Yuan Tang, Yitian Qian
New York University, United States · Carnegie Mellon University, United States · Boston University, United States