# BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation

arXiv: https://arxiv.org/abs/2604.03159 · HTML: https://mlsanity.com/paper/2604.03159/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 31 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Do Language Models Know When They're Hallucinating References?](https://mlsanity.com/paper/2305.18248/) (2023)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [Autorubric: A Unifying Framework for Rubric-Based LLM Evaluation on Non-Verifiable Tasks](https://mlsanity.com/paper/2603.00077/) (2026)
- [HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences](https://mlsanity.com/paper/2601.18724/) (2026)
- [Large Language Models Reflect Human Citation Patterns with a Heightened Citation Bias](https://mlsanity.com/paper/2405.15739/) (2024)
- [Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025](https://mlsanity.com/paper/2602.05930/) (2026)
- [CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era](https://mlsanity.com/paper/2602.23452/) (2026)
- [GhostCite: A Large-Scale Analysis of Citation Validity in the Age of Large Language Models](https://mlsanity.com/paper/2602.06718/) (2026)
- [CiteGuard: Faithful Citation Attribution for LLMs via Retrieval-Augmented Validation](https://mlsanity.com/paper/2510.17853/) (2025)
- [BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature](https://mlsanity.com/paper/2601.16993/) (2026)
- [CheckIfExist: Detecting Citation Hallucinations in the Era of AI-Generated Content](https://mlsanity.com/paper/2602.15871/) (2026)
- [Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy](https://mlsanity.com/paper/2510.25378/) (2025)
- [CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery](https://mlsanity.com/paper/2602.23075/) (2026)
- [Structural Hallucination in Large Language Models: A Network-Based Evaluation of Knowledge Organization and Citation Integrity](https://mlsanity.com/paper/2603.01341/) (2026)
- [Unmediated AI-Assisted Scholarly Citations](https://mlsanity.com/paper/2602.01686/) (2026)

## Built on by (most cited first, 2 of 2)

- [HALLMARK: How to Diagnose LLM Citation Verifiers and When to Deploy Them](https://mlsanity.com/paper/2607.18360/) (2026)
- [Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences](https://mlsanity.com/paper/2607.00738/) (2026)

## Abstract (arXiv)

Large language models with web search are increasingly used in scientific publishing agents, yet they produce BibTeX entries with pervasive field-level errors stemming from omission, partial corruption, substitution, and hallucination. We construct a benchmark of 931 papers across four domains and three citation tiers---popular, low-citation, and recent post-cutoff---with version-aware ground truth. Three search-enabled frontier models (GPT-5, Claude Sonnet-4.6, Gemini-3 Flash) generate approximately 23,000 field-level observations. Overall accuracy is 83.6%, but only 50.9% of entries are fully correct; accuracy drops 27.7 pp from popular to recent papers, revealing heavy reliance on parametric memory even when search is available. Co-occurrence analysis identifies two failure modes: wholesale entry substitution and isolated field error. We present clibib, an open-source tool for deterministic BibTeX retrieval, as a mitigation mechanism. Two-stage integration raises accuracy to 91.5% (+8.0 pp) and fully correct entries to 78.3%, with a 0.8% regression rate. Separating search from revision yields larger gains and lower regression than single-stage tool loops (0.8% vs. 4.8%), demonstrating that integration architecture matters independently of model/tool capability. We release clibib and an accompanying agent skill under the MIT License to improve citation accuracy in increasingly automated scientific workflows.