CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery

TL;DR

CiteLLM is a secure, local-agent platform that enhances trustworthy scientific reference discovery by integrating LLM utilities within LaTeX editors, ensuring privacy, integrity, and accurate citations.

Contribution

This work introduces CiteLLM, a novel agentic platform that embeds LLMs in LaTeX environments for trustworthy, privacy-preserving reference discovery using dynamic routing and semantic validation.

Findings

Superior accuracy in returning valid references

Effective filtering from trusted repositories

Seamless integration within LaTeX editors

Abstract

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.