# HalluGuard: Demystifying Data-Driven and Reasoning-Driven Hallucinations in LLMs

arXiv: https://arxiv.org/abs/2601.18753 · HTML: https://mlsanity.com/paper/2601.18753/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 9 of its 62 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

- LLM reasoning / [Hallucination detection and mitigation](https://mlsanity.com/lr/hallucination-detection-and-mitigation/)

## Builds on (most cited first, 9 of 9)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [Shadows in the Attention: Contextual Perturbation and Representation Drift in the Dynamics of Hallucination in LLMs](https://mlsanity.com/paper/2505.16894/) (2025)
- [D2HScore: Reasoning-Aware Hallucination Detection via Semantic Breadth and Depth Analysis in LLMs](https://mlsanity.com/paper/2509.11569/) (2025)
- [Principled Detection of Hallucinations in Large Language Models via Multiple Testing](https://mlsanity.com/paper/2508.18473/) (2025)

## Built on by (most cited first, 5 of 5)

- [DynaWeb: Model-Based Reinforcement Learning of Web Agents](https://mlsanity.com/paper/2601.22149/) (2026)
- [RoboRouter: Training-Free Policy Routing for Robotic Manipulation](https://mlsanity.com/paper/2603.07892/) (2026)
- [Reasoning Consensus: Structural Ensembling of LLM Reasoning via Weighted DAG Aggregation](https://mlsanity.com/paper/2607.27783/) (2026)
- [TRACE: Tourism Recommendation with Accountable Citation Evidence](https://mlsanity.com/paper/2605.07677/) (2026)
- [CareGuardAI: Context-Aware Multi-Agent Guardrails for Clinical Safety & Hallucination Mitigation in Patient-Facing LLMs](https://mlsanity.com/paper/2604.26959/) (2026)

## Abstract (arXiv)

The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations. These failures typically stem from two sources: data-driven hallucinations and reasoning-driven hallucinations. However, existing detection methods usually address only one source and rely on task-specific heuristics, limiting their generalization to complex scenarios. To overcome these limitations, we introduce the Hallucination Risk Bound, a unified theoretical framework that formally decomposes hallucination risk into data-driven and reasoning-driven components, linked respectively to training-time mismatches and inference-time instabilities. This provides a principled foundation for analyzing how hallucinations emerge and evolve. Building on this foundation, we introduce HalluGuard, an NTK-based score that leverages the induced geometry and captured representations of the NTK to jointly identify data-driven and reasoning-driven hallucinations. We evaluate HalluGuard on 10 diverse benchmarks, 11 competitive baselines, and 9 popular LLM backbones, consistently achieving state-of-the-art performance in detecting diverse forms of LLM hallucinations. We open-source our proposed model model at https://github.com/Susan571/HalluGuard-ICLR2026.