# PoLLMgraph: Unraveling Hallucinations in Large Language Models via State Transition Dynamics

arXiv: https://arxiv.org/abs/2404.04722 · HTML: https://mlsanity.com/paper/2404.04722/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 6 Apr 2024.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation](https://mlsanity.com/paper/2305.14251/) (2023)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [Teaching Models to Express Their Uncertainty in Words](https://mlsanity.com/paper/2205.14334/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Self-critiquing models for assisting human evaluators](https://mlsanity.com/paper/2206.05802/) (2022)
- [A Survey of Hallucination in Large Foundation Models](https://mlsanity.com/paper/2309.05922/) (2023)
- [FEQA: A Question Answering Evaluation Framework for Faithfulness Assessment in Abstractive Summarization](https://mlsanity.com/paper/2005.03754/) (2020)
- [Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics](https://mlsanity.com/paper/2104.13346/) (2021)
- [On Hallucination and Predictive Uncertainty in Conditional Language Generation](https://mlsanity.com/paper/2103.15025/) (2021)
- [LM vs LM: Detecting Factual Errors via Cross Examination](https://mlsanity.com/paper/2305.13281/) (2023)
- [Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation](https://mlsanity.com/paper/2305.15852/) (2023)
- [Handling Divergent Reference Texts when Evaluating Table-to-Text Generation](https://mlsanity.com/paper/1906.01081/) (2019)
- [A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection](https://mlsanity.com/paper/2310.06498/) (2023)

## Built on by (most cited first, 14 of 14)

- [Get my drift? Catching LLM Task Drift with Activation Deltas](https://mlsanity.com/paper/2406.00799/) (2024)
- [Hallucination Detection in LLMs Using Spectral Features of Attention Maps](https://mlsanity.com/paper/2502.17598/) (2025)
- [Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs](https://mlsanity.com/paper/2505.17656/) (2025)
- [SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs](https://mlsanity.com/paper/2503.05980/) (2025)
- [TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention](https://mlsanity.com/paper/2503.10602/) (2025)
- [Zero-resource Hallucination Detection for Text Generation via Graph-based Contextual Knowledge Triples Modeling](https://mlsanity.com/paper/2409.11283/) (2024)
- [HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs](https://mlsanity.com/paper/2506.00088/) (2025)
- [Beyond Policy Optimization: A Data Curation Flywheel for Sparse-Reward Long-Horizon Planning](https://mlsanity.com/paper/2508.03018/) (2025)
- [A Debate-Driven Experiment on LLM Hallucinations and Accuracy](https://mlsanity.com/paper/2410.19485/) (2024)
- [From Signals to Transfer: A Factorised Study of Probe-Based Uncertainty Estimation in Large Language Models](https://mlsanity.com/paper/2606.27679/) (2026)
- [Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor](https://mlsanity.com/paper/2507.15903/) (2025)
- [LANCET: Neural Intervention via Structural Entropy for Mitigating Faithfulness Hallucinations in LLMs](https://mlsanity.com/paper/2601.01401/) (2026)
- [When Do Hallucinations Arise? A Graph Perspective on the Evolution of Path Reuse and Path Compression](https://mlsanity.com/paper/2604.03557/) (2026)
- [TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction](https://mlsanity.com/paper/2605.18163/) (2026)

## Abstract (arXiv)

Despite tremendous advancements in large language models (LLMs) over recent years, a notably urgent challenge for their practical deployment is the phenomenon of hallucination, where the model fabricates facts and produces non-factual statements. In response, we propose PoLLMgraph, a Polygraph for LLMs, as an effective model-based white-box detection and forecasting approach. PoLLMgraph distinctly differs from the large body of existing research that concentrates on addressing such challenges through black-box evaluations. In particular, we demonstrate that hallucination can be effectively detected by analyzing the LLM's internal state transition dynamics during generation via tractable probabilistic models. Experimental results on various open-source LLMs confirm the efficacy of PoLLMgraph, outperforming state-of-the-art methods by a considerable margin, evidenced by over 20% improvement in AUC-ROC on common benchmarking datasets like TruthfulQA. Our work paves a new way for model-based white-box analysis of LLMs, motivating the research community to further explore, understand, and refine the intricate dynamics of LLM behaviors.