# Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents

arXiv: https://arxiv.org/abs/2604.03173 · HTML: https://mlsanity.com/paper/2604.03173/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 40 of its 53 references that are in the map.
- First posted on arXiv 3 Apr 2026.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 40)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [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)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [Teaching language models to support answers with verified quotes](https://mlsanity.com/paper/2203.11147/) (2022)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [Measuring Attribution in Natural Language Generation Models](https://mlsanity.com/paper/2112.12870/) (2021)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [Large Legal Fictions: Profiling Legal Hallucinations in Large Language Models](https://mlsanity.com/paper/2401.01301/) (2024)
- [Do Language Models Know When They're Hallucinating References?](https://mlsanity.com/paper/2305.18248/) (2023)
- [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://mlsanity.com/paper/2212.08037/) (2022)
- [ExpertQA: Expert-Curated Questions and Attributed Answers](https://mlsanity.com/paper/2309.07852/) (2023)
- [LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-context QA](https://mlsanity.com/paper/2409.02897/) (2024)
- [CiteME: Can Language Models Accurately Cite Scientific Claims?](https://mlsanity.com/paper/2407.12861/) (2024)
- [Effective Large Language Model Adaptation for Improved Grounding and Citation Generation](https://mlsanity.com/paper/2311.09533/) (2023)
- [HALoGEN: Fantastic LLM Hallucinations and Where to Find Them](https://mlsanity.com/paper/2501.08292/) (2025)
- [CiteEval: Principle-Driven Citation Evaluation for Source Attribution](https://mlsanity.com/paper/2506.01829/) (2025)
- [HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences](https://mlsanity.com/paper/2601.18724/) (2026)
- [Correctness is not Faithfulness in RAG Attributions](https://mlsanity.com/paper/2412.18004/) (2024)
- [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)

## Built on by (most cited first, 6 of 6)

- [HALLMARK: How to Diagnose LLM Citation Verifiers and When to Deploy Them](https://mlsanity.com/paper/2607.18360/) (2026)
- [Verified Misguidance: Measuring Structural Citation Failures in Search-Augmented LLMs](https://mlsanity.com/paper/2605.28565/) (2026)
- [Per-Entity Bias Mapping for AI Visibility: Why Brand Mentions Require Entity-Specific Calibration](https://mlsanity.com/paper/2606.21595/) (2026)
- [Is this Citation on Point?](https://mlsanity.com/paper/2608.12571/) (2026)
- [Characterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses](https://mlsanity.com/paper/2609.19244/) (2026)
- [AgentSWE: Can Coding Agents Build the Agent You Actually Want?](https://mlsanity.com/paper/2610.13361/) (2026)

## Abstract (arXiv)

Large language models and deep research agents supply citation URLs to support their claims, yet the reliability of these citations has not been systematically measured. We address six research questions about citation URL validity using 10 models and agents on DRBench (53,090 URLs) and 3 models on ExpertQA (168,021 URLs across 32 academic fields). We find that 3--13% of citation URLs are hallucinated -- they have no record in the Wayback Machine and likely never existed -- while 5--18% are non-resolving overall. Deep research agents generate substantially more citations per query than search-augmented LLMs but hallucinate URLs at higher rates. Domain effects are pronounced: non-resolving rates range from 5.4% (Business) to 11.4% (Theology), with per-model effects even larger. Decomposing failures reveals that some models fabricate every non-resolving URL, while others show substantial link-rot fractions indicating genuine retrieval. As a solution, we release urlhealth, an open-source tool for URL liveness checking and stale-vs-hallucinated classification using the Wayback Machine. In agentic self-correction experiments, models equipped with urlhealth reduce non-resolving citation URLs by 6textrm--79× to under 1%, though effectiveness depends on the model's tool-use competence. The tool and all data are publicly available. Our characterization findings, failure taxonomy, and open-source tooling establish that citation URL validity is both measurable at scale and correctable in practice.