# Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing

arXiv: https://arxiv.org/abs/2609.21096 · HTML: https://mlsanity.com/paper/2609.21096/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 24 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Builds on (most cited first, 21 of 21)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions](https://mlsanity.com/paper/2311.05232/) (2023)
- [On Faithfulness and Factuality in Abstractive Summarization](https://mlsanity.com/paper/2005.00661/) (2020)
- [Latent Retrieval for Weakly Supervised Open Domain Question Answering](https://mlsanity.com/paper/1906.00300/) (2019)
- [On the Bottleneck of Graph Neural Networks and its Practical Implications](https://mlsanity.com/paper/2006.05205/) (2020)
- [Understanding over-squashing and bottlenecks on graphs via curvature](https://mlsanity.com/paper/2111.14522/) (2021)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection](https://mlsanity.com/paper/2402.03744/) (2024)
- [Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety](https://mlsanity.com/paper/2507.11473/) (2025)
- [Out-of-Distribution Detection and Selective Generation for Conditional Language Models](https://mlsanity.com/paper/2209.15558/) (2022)
- [Transformers need glasses! Information over-squashing in language tasks](https://mlsanity.com/paper/2406.04267/) (2024)
- [When to Trust LLMs: Aligning Confidence with Response Quality](https://mlsanity.com/paper/2404.17287/) (2024)
- [Hallucination Detection in LLMs Using Spectral Features of Attention Maps](https://mlsanity.com/paper/2502.17598/) (2025)
- [Towards Improving Faithfulness in Abstractive Summarization](https://mlsanity.com/paper/2210.01877/) (2022)
- [Hallucination Detection in LLMs with Topological Divergence on Attention Graphs](https://mlsanity.com/paper/2504.10063/) (2025)
- [PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model](https://mlsanity.com/paper/2501.12206/) (2025)
- [Minimal angle spread in the probability simplex with respect to the uniform distribution](https://mlsanity.com/paper/2105.08653/) (2021)

## Abstract (arXiv)

In this work, we examine the topology of information flow patterns within attention graphs to effectively distinguish hallucinated from non-hallucinated responses. We analyze the Forman-Ricci curvature to identify structural patterns indicating information bottlenecks in attention graphs. We then introduce a method that captures both semi-local and global information-flow characteristics of attention heads associated with hallucinated responses. We evaluate our approach extensively across several LLMs and established benchmarks. Empirical results demonstrate that our proposed single-pass approach provides consistent improvements over existing attention-based and multi-response baselines across two hallucination-detection benchmarks, while achieving competitive performance across diverse LLM architectures. Further analysis reveals that impaired context sharing among tokens during causal generation is strongly associated with hallucination occurrences in LLMs. In particular, hallucinated responses are consistently characterized by an over-reliance on self-attention, diffused context retrieval from earlier tokens, or information over-squashing, especially in the final transformer layer.