# Real-Time Detection of Hallucinated Entities in Long-Form Generation

arXiv: https://arxiv.org/abs/2509.03531 · HTML: https://mlsanity.com/paper/2509.03531/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Builds on (most cited first, 25 of 25)

- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [Understanding intermediate layers using linear classifier probes](https://mlsanity.com/paper/1610.01644/) (2016)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation](https://mlsanity.com/paper/2302.09664/) (2023)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs](https://mlsanity.com/paper/2406.15927/) (2024)
- [FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://mlsanity.com/paper/2307.13528/) (2023)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Unsupervised Quality Estimation for Neural Machine Translation](https://mlsanity.com/paper/2005.10608/) (2020)
- [Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming](https://mlsanity.com/paper/2501.18837/) (2025)
- [Long-form factuality in large language models](https://mlsanity.com/paper/2403.18802/) (2024)
- [Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models](https://mlsanity.com/paper/2411.14257/) (2024)
- [LLM Internal States Reveal Hallucination Risk Faced With a Query](https://mlsanity.com/paper/2407.03282/) (2024)
- [Do Androids Know They're Only Dreaming of Electric Sheep?](https://mlsanity.com/paper/2312.17249/) (2023)
- [Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2208.05309/) (2022)
- [Investigating task-specific prompts and sparse autoencoders for activation monitoring](https://mlsanity.com/paper/2504.20271/) (2025)
- [HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection](https://mlsanity.com/paper/2502.11948/) (2025)
- [FactCheckmate: Preemptively Detecting and Mitigating Hallucinations in LMs](https://mlsanity.com/paper/2410.02899/) (2024)

## Built on by (most cited first, 30 of 34)

- [Steering MoE LLMs via Expert (De)Activation](https://mlsanity.com/paper/2509.09660/) (2025)
- [Entropy Alone is Insufficient for Safe Selective Prediction in LLMs](https://mlsanity.com/paper/2603.21172/) (2026)
- [Interpretability Can Be Actionable](https://mlsanity.com/paper/2605.11161/) (2026)
- [Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning](https://mlsanity.com/paper/2510.02324/) (2025)
- [Lost in Stories: Consistency Bugs in Long Story Generation by LLMs](https://mlsanity.com/paper/2603.05890/) (2026)
- [Reference-Free Rating of LLM Responses via Latent Information](https://mlsanity.com/paper/2509.24678/) (2025)
- [Semantic Self-Distillation for Language Model Uncertainty](https://mlsanity.com/paper/2602.04577/) (2026)
- [Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation](https://mlsanity.com/paper/2510.18439/) (2025)
- [PARALLAX: Separating Genuine Hallucination Detection from Benchmark Construction Artifacts](https://mlsanity.com/paper/2605.17028/) (2026)
- [Neural Probe-Based Hallucination Detection for Large Language Models](https://mlsanity.com/paper/2512.20949/) (2025)
- [Do I Really Know? Learning Factual Self-Verification for Hallucination Reduction](https://mlsanity.com/paper/2602.02018/) (2026)
- [Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing](https://mlsanity.com/paper/2606.00033/) (2026)
- [From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2606.27679/) (2026)
- [Mark, Don't Erase: Token Inoculation for Dual-Use Knowledge in LLMs](https://mlsanity.com/paper/2607.18639/) (2026)
- [Prompt Embedding Probes (PEP): Hallucination Detection in LLMs from Hidden States](https://mlsanity.com/paper/2608.08024/) (2026)
- [Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique](https://mlsanity.com/paper/2608.10430/) (2026)
- [Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection](https://mlsanity.com/paper/2601.19245/) (2026)
- [Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models](https://mlsanity.com/paper/2601.21214/) (2026)
- [Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning](https://mlsanity.com/paper/2602.14518/) (2026)
- [ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention](https://mlsanity.com/paper/2603.22016/) (2026)
- [A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification](https://mlsanity.com/paper/2604.11662/) (2026)
- [RAGognizer: Hallucination-Aware Fine-Tuning via Detection Head Integration](https://mlsanity.com/paper/2604.15945/) (2026)
- [Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics](https://mlsanity.com/paper/2606.12476/) (2026)
- [Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale](https://mlsanity.com/paper/2607.07670/) (2026)
- [Temporal Multi-Signal Fusion for Token-Level Hallucination Detection](https://mlsanity.com/paper/2608.18115/) (2026)
- [Scalable Token-Level Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2605.12384/) (2026)
- [Entropy Distribution as a Fingerprint for Hallucinations in Generative Models](https://mlsanity.com/paper/2605.28264/) (2026)
- [Building Reliable Long-Form Generation via Hallucination Rejection Sampling](https://mlsanity.com/paper/2606.03628/) (2026)
- [NeuroCogMap Reveals Cognitive Organization of Large Language Models](https://mlsanity.com/paper/2607.00397/) (2026)
- [Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering](https://mlsanity.com/paper/2607.13568/) (2026)

## Abstract (arXiv)

Large language models are now routinely used in high-stakes applications where hallucinations can cause serious harm, such as medical consultations or legal advice. Existing hallucination detection methods, however, are impractical for real-world use, as they are either limited to short factual queries or require costly external verification. We present a cheap, scalable method for real-time identification of hallucinated tokens in long-form generations, and scale it effectively to 70B parameter models. Our approach targets entity-level hallucinations-e.g., fabricated names, dates, citations-rather than claim-level, thereby naturally mapping to token-level labels and enabling streaming detection. We develop an annotation methodology that leverages web search to annotate model responses with grounded labels indicating which tokens correspond to fabricated entities. This dataset enables us to train effective hallucination classifiers with simple and efficient methods such as linear probes. Evaluating across four model families, our classifiers consistently outperform baselines on long-form responses, including more expensive methods such as semantic entropy (e.g., AUC 0.90 vs 0.71 for Llama-3.3-70B), and are also an improvement in short-form question-answering settings. Despite being trained only to detect hallucinated entities, our probes effectively detect incorrect answers in mathematical reasoning tasks, indicating generalization beyond entities. While our annotation methodology is expensive, we find that annotated responses from one model can be used to train effective classifiers on other models; accordingly, we publicly release our datasets to facilitate reuse. Overall, our work suggests a promising new approach for scalable, real-world hallucination detection.