Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection

arXiv:2605.08583 · cs.CL · Submitted 2026-05-09 · Read on arXiv

cs.CL

Submitted: 2026-05-09

Updated: 2026-10-13

Code: https://github.com/aaFrostnova/CiteTracer

Terminology

• Benchmark — 2× in this paper · explained in 2 episodes
• Hallucination — 2× in this paper · explained in 4 episodes
• Hallucination Detection — 2× in this paper · explained in 2 episodes
• Verification — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• F1 Score — 1× in this paper · explained in 3 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes

Sources

• Learning Soft Linear Constraints with Application to Citation Field Extraction
• Qwen3-VL Technical Report
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• AutoData: A Multi-Agent System for Open Web Data Collection
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era
• Web Retrieval Agents for Evidence-Based Misinformation Detection
• A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
• DeepSeek-OCR 2: Visual Causal Flow

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering