# The Geometry of Truth: Layer-wise Semantic Dynamics for Hallucination Detection in Large Language Models

arXiv: https://arxiv.org/abs/2510.04933 · HTML: https://mlsanity.com/paper/2510.04933/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 15 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [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)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback](https://mlsanity.com/paper/2302.12813/) (2023)
- [Linear Representations of Sentiment in Large Language Models](https://mlsanity.com/paper/2310.15154/) (2023)
- [Analyzing Transformers in Embedding Space](https://mlsanity.com/paper/2209.02535/) (2022)

## Built on by (most cited first, 7 of 7)

- [DRIFT: Detecting Representational Inconsistencies for Factual Truthfulness](https://mlsanity.com/paper/2601.14210/) (2026)
- [The Surprising Universality of LLM Outputs: A Real-Time Verification Primitive](https://mlsanity.com/paper/2604.25634/) (2026)
- [A Geometric Taxonomy of Hallucinations in LLMs](https://mlsanity.com/paper/2602.13224/) (2026)
- [FinReflectKG -- HalluBench: GraphRAG Hallucination Benchmark for Financial Question Answering Systems](https://mlsanity.com/paper/2603.20252/) (2026)
- [EcoThink: A Green Adaptive Inference Framework for Sustainable and Accessible Agents](https://mlsanity.com/paper/2603.25498/) (2026)
- [Riemannian Geometry for Pre-trained Language Model Embeddings](https://mlsanity.com/paper/2607.07047/) (2026)
- [HalluTracer: Pre-Decoding Truthfulness Prediction via Depth-Averaged Probe-Logit](https://mlsanity.com/paper/2608.16353/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for hallucination detection that analyzes the evolution of hidden-state semantics across transformer layers. Unlike prior methods that rely on multiple sampling passes or external verification sources, LSD operates intrinsically within the model's representational space. Using margin-based contrastive learning, LSD aligns hidden activations with ground-truth embeddings derived from a factual encoder, revealing a distinct separation in semantic trajectories: factual responses preserve stable alignment, while hallucinations exhibit pronounced semantic drift across depth. Evaluated on the TruthfulQA and synthetic factual-hallucination datasets, LSD achieves an F1-score of 0.92, AUROC of 0.96, and clustering accuracy of 0.89, outperforming SelfCheckGPT and Semantic Entropy baselines while requiring only a single forward pass. This efficiency yields a 5-20x speedup over sampling-based methods without sacrificing precision or interpretability. LSD offers a scalable, model-agnostic mechanism for real-time hallucination monitoring and provides new insights into the geometry of factual consistency within large language models.