# Hallucination Detection in LLMs with Topological Divergence on Attention Graphs

arXiv: https://arxiv.org/abs/2504.10063 · HTML: https://mlsanity.com/paper/2504.10063/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 71 references that are in the map.
- First posted on arXiv 14 Apr 2025.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarization](https://mlsanity.com/paper/1808.08745/) (2018)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond](https://mlsanity.com/paper/1602.06023/) (2016)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [The Internal State of an LLM Knows When It's Lying](https://mlsanity.com/paper/2304.13734/) (2023)
- [Deep learning for time series classification: a review](https://mlsanity.com/paper/1809.04356/) (2018)
- [Trusting Your Evidence: Hallucinate Less with Context-aware Decoding](https://mlsanity.com/paper/2305.14739/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations](https://mlsanity.com/paper/2410.02707/) (2024)
- [Analyzing the Structure of Attention in a Transformer Language Model](https://mlsanity.com/paper/1906.04284/) (2019)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [An introduction to Topological Data Analysis: fundamental and practical aspects for data scientists](https://mlsanity.com/paper/1710.04019/) (2017)
- [Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification](https://mlsanity.com/paper/2403.04696/) (2024)
- [Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities](https://mlsanity.com/paper/2405.20003/) (2024)
- [Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps](https://mlsanity.com/paper/2407.07071/) (2024)
- [Hallucinated but Factual! Inspecting the Factuality of Hallucinations in Abstractive Summarization](https://mlsanity.com/paper/2109.09784/) (2021)
- [Why do LLMs attend to the first token?](https://mlsanity.com/paper/2504.02732/) (2025)
- [Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts](https://mlsanity.com/paper/2306.04723/) (2023)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models](https://mlsanity.com/paper/2405.09589/) (2024)
- [Successor Heads: Recurring, Interpretable Attention Heads In The Wild](https://mlsanity.com/paper/2312.09230/) (2023)
- [Do Androids Know They're Only Dreaming of Electric Sheep?](https://mlsanity.com/paper/2312.17249/) (2023)
- [Artificial Text Detection via Examining the Topology of Attention Maps](https://mlsanity.com/paper/2109.04825/) (2021)

## Built on by (most cited first, 19 of 19)

- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs](https://mlsanity.com/paper/2505.16894/) (2025)
- [HALT: Hallucination Assessment via Log-probs as Time series](https://mlsanity.com/paper/2602.02888/) (2026)
- [Neural Message-Passing on Attention Graphs for Hallucination Detection](https://mlsanity.com/paper/2509.24770/) (2025)
- [Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration](https://mlsanity.com/paper/2601.06160/) (2026)
- [HalluZig: Hallucination Detection using Zigzag Persistence](https://mlsanity.com/paper/2601.01552/) (2026)
- [Probabilistic distances-based hallucination detection in LLMs with RAG](https://mlsanity.com/paper/2506.09886/) (2025)
- [Pre-Generation Hallucination Detection in Large Language Models via Soft-Target Attention Probing](https://mlsanity.com/paper/2606.21917/) (2026)
- [Enhancing the Reliability of Medical AI through Expert-guided Uncertainty Modeling](https://mlsanity.com/paper/2604.01898/) (2026)
- [Uncertainty Estimation for the Open-Set Text Classification systems](https://mlsanity.com/paper/2604.08560/) (2026)
- [Attention Sinks as Internal Signals for Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2604.10697/) (2026)
- [Topology-Aware Layer Pruning for Large Vision-Language Models](https://mlsanity.com/paper/2604.16502/) (2026)
- [Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics](https://mlsanity.com/paper/2605.04893/) (2026)
- [ASK-NN: An Asymmetric Nearest-Neighbor Test that detects Distribution Drifts in Natural Language](https://mlsanity.com/paper/2607.15607/) (2026)
- [SIRIN: A Unified Toolkit for Detecting Contextual Hallucinations in Retrieval-Augmented and Memory-Grounded LLM Systems](https://mlsanity.com/paper/2608.00033/) (2026)
- [CodeTD: Topology of Attention Detects Hallucinations in Code LLMs](https://mlsanity.com/paper/2609.07779/) (2026)
- [Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing](https://mlsanity.com/paper/2609.21096/) (2026)
- [Mixed-Prior Decision Risk for Open-Set Recognition](https://mlsanity.com/paper/2609.35043/) (2026)
- [Spectral Geometry of Attention: From Information Routing to Uncertainty](https://mlsanity.com/paper/2610.06012/) (2026)

## Abstract (arXiv)

Hallucination, i.e., generating factually incorrect content, remains a critical challenge for large language models (LLMs). We introduce TOHA, a TOpology-based HAllucination detector in the RAG setting, which leverages a topological divergence metric to quantify the structural properties of graphs induced by attention matrices. Examining the topological divergence between prompt and response subgraphs reveals consistent patterns: higher divergence values in specific attention heads correlate with hallucinated outputs, independent of the dataset. Extensive experiments - including evaluation on question answering and summarization tasks - show that our approach achieves state-of-the-art or competitive results on several benchmarks while requiring minimal annotated data and computational resources. Our findings suggest that analyzing the topological structure of attention matrices can serve as an efficient and robust indicator of factual reliability in LLMs.