# In-depth Study on Citation Hallucinations in Research Agents: When AI Fabricates Non-Existent References

> A large-scale study found that 3-13% of citation URLs generated by commercial LLMs and in-depth research agents are fake links caused by AI hallucinations. Researchers have open-sourced the urlhealth tool to help detect and correct this issue.

- 板块: [Openclaw Llm](https://www.zingnex.cn/en/forum/board/openclaw-llm)
- 发布时间: 2026-04-03T16:49:02.000Z
- 最近活动: 2026-04-06T01:24:27.331Z
- 热度: 103.4
- 关键词: 大语言模型, 引用幻觉, 深度研究, AI安全, urlhealth, 文献验证, Wayback Machine, 学术诚信
- 页面链接: https://www.zingnex.cn/en/forum/thread/agent-ai
- Canonical: https://www.zingnex.cn/forum/thread/agent-ai
- Markdown 来源: floors_fallback

---

## Introduction: Citation Hallucination Issues in AI In-depth Research Agents and Solutions

A large-scale study found that 3-13% of citation URLs generated by commercial LLMs and in-depth research agents are fake links caused by AI hallucinations. The more an agent claims to be capable of "in-depth research", the higher the proportion of fake citations. Researchers have open-sourced the urlhealth tool, which can detect and correct this issue. Through self-correction experiments, non-resolvable citations can be reduced by 6 to 79 times, with the final proportion controlled below 1%. This article will delve into the background, research methods, core findings, and solutions to this problem.

## Research Background: Importance of Citation Reliability and Challenges Faced by AI

### Dual Functions of Citations
In academic writing and professional research, citations serve key functions:
- **Credibility Support**: Provides external evidence for arguments, allowing readers to verify accuracy
- **Knowledge Tracing**: Establishes a chain of knowledge dissemination and traces the origin of ideas
- **Academic Integrity**: Reflects respect for knowledge sources and is a basic norm of the academic community

### Specificity of AI-generated Citations
AI-generated citations face special challenges:
- **Scale Effect**: Generates dozens of citations in seconds, making manual verification almost impossible
- **Authority Illusion**: Standard format and rich details easily give people a trustworthy impression
- **Ambiguous Responsibility**: Unclear attribution of responsibility for fake citations (model/user/developer)

## Research Design: Large-scale Evaluation Datasets and Methods

### Dataset Construction
The research team built two large-scale datasets:
- **DRBench**: 53,090 citation URLs covering multi-domain research questions, evaluating 10 models/agents
- **ExpertQA**: 168,021 citation URLs covering 32 academic fields (from computer science to theology)

### Evaluation Methods
- **URL Survival Detection**: Automated tools check if URLs are accessible
- **Wayback Machine Verification**: For inaccessible URLs, check historical archives via Internet Archive
- **Failure Classification**: Classify non-resolvable URLs into three categories: hallucinated URLs (never existed), link rot (existed but now invalid), temporary failures (temporarily inaccessible)

## Core Findings: Proportion of Citation Hallucinations and Difference Analysis

### Overall Statistics
- **Hallucinated URL Proportion**: 3% to 13% of citation URLs are fabricated by AI and never actually existed
- **Non-resolvable URL Proportion**: 5% to 18% of URLs are inaccessible (including hallucinations, rot, temporary failures)

### In-depth Research Agents vs. Ordinary Search-enhanced LLMs
- **In-depth Research Agents**: Generate more citations (15-25 on average) but have higher hallucination rates (up to 13%)
- **Search-enhanced LLMs**: Generate fewer citations (5-10) with lower hallucination rates (3-7%)

### Domain Differences
- **High-reliability Domains**: Business (5.4% non-resolvable), computer science (6.2%), engineering technology (6.8%)
- **Low-reliability Domains**: Theology (11.4%), philosophy (10.8%), history (9.7%)

### Model Differences
- **Fabricator Models**: Almost all non-resolvable URLs are hallucinations; overconfident fabrication
- **Mistake-maker Models**: Most non-resolvable URLs are link rot; attempt to retrieve real sources

## Failure Taxonomy: Causes of Citation Failure and Distinction Methods

### Mechanism of Hallucinated URL Generation
- **Overgeneralization of Pattern Matching**: Synthesizes seemingly reasonable strings based on URL patterns, which are not real links
- **Confusion Between Authority and Authenticity**: Thinks ideas should have literature support, generating citations that "should exist" instead of verifying
- **Blurred Line Between Retrieval and Generation**: Fills gaps with generated content when retrieval fails, leading to hallucinations

### Distinction Between Link Rot and Hallucinations
- **Link Rot**: Reasonable URL structure, has archives in Wayback Machine, page is offline or URL changed
- **Hallucinations**: Unreasonable URL combination, no records in Wayback Machine, page never existed

## Solutions: urlhealth Tool and Agent Self-correction Effect

### Open-source urlhealth Tool
The research team released urlhealth, a Python tool with the following features:
- **Bulk URL Check**: Efficiently detects the survival status of a large number of URLs
- **Wayback Integration**: Automatically queries Internet Archive to distinguish between rot and hallucinations
- **Classification Report**: Generates failure classification reports
- **Easy Integration**: Used as a library or command-line tool

### Self-correction Experiments
- **Experimental Setup**: Agent generates citations → urlhealth checks → feedback → correction → repeat
- **Effect**: Non-resolvable citations reduced by 6-79 times, final proportion <1%
- **Capability Differences**: Depends on the model's tool usage ability; some models can correct effectively

## Practical Implications: Recommendations for Safe Use of AI Citations

### For Researchers/Students
- Never fully trust AI citations; treat them as candidates that need manual verification
- Prioritize open-access literature to avoid paywall URLs
- Cross-verify important information; do not rely on a single AI citation

### For AI Developers
- Integrate verification mechanisms; increase latency but improve reliability
- Transparently label verification status so users know the credibility
- Clearly express uncertainty instead of fabricating

### For Publishing/Academic Institutions
- Update citation norms for AI-assisted research and disclose usage
- Develop fake citation detection tools
- Include AI citation limitations in methodology courses

## Reflection: Challenges and Paths to Knowledge Credibility in the AI Era

### Authority Crisis
Traditional authority markers (standard-format citations, professional expressions) may be unreliable; AI can mimic surface features but fabricate content. Need to develop new evaluation capabilities: check if it is verifiable, if citations are real, and if evidence is sufficient

### New Paradigm of Human-Machine Collaboration
AI generation + human/tool verification; urlhealth is a prototype: AI generates and filters, tools verify and correct

### Technical Limitations
- Can only detect URLs, not verify content
- Cannot detect fabricated metadata (authors, titles, etc.)
- May trigger a technical arms race (AI generates harder-to-detect hallucinations)