# Is LLMs Hallucination Usable? LLM-based Negative Reasoning for Fake News Detection

arXiv: https://arxiv.org/abs/2503.09153 · HTML: https://mlsanity.com/paper/2503.09153/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Hallucination detection and mitigation, one of 17 directions in LLM reasoning.
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

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

## Builds on (most cited first, 13 of 13)

- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond](https://mlsanity.com/paper/2304.13712/) (2023)
- ["Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection](https://mlsanity.com/paper/1705.00648/) (2017)
- [The Unreliability of Explanations in Few-shot Prompting for Textual Reasoning](https://mlsanity.com/paper/2205.03401/) (2022)
- [Towards LLM-based Fact Verification on News Claims with a Hierarchical Step-by-Step Prompting Method](https://mlsanity.com/paper/2310.00305/) (2023)
- [Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection](https://mlsanity.com/paper/2309.12247/) (2023)
- [Explainable Fake News Detection With Large Language Model via Defense Among Competing Wisdom](https://mlsanity.com/paper/2405.03371/) (2024)
- [Towards LLM-guided Causal Explainability for Black-box Text Classifiers](https://mlsanity.com/paper/2309.13340/) (2023)
- [Make LLM a Testing Expert: Bringing Human-like Interaction to Mobile GUI Testing via Functionality-aware Decisions](https://mlsanity.com/paper/2310.15780/) (2023)
- [Jointly embedding the local and global relations of heterogeneous graph for rumor detection](https://mlsanity.com/paper/1909.04465/) (2019)
- [JustiLM: Few-shot Justification Generation for Explainable Fact-Checking of Real-world Claims](https://mlsanity.com/paper/2401.08026/) (2024)
- [GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with Masking](https://mlsanity.com/paper/2312.05739/) (2023)
- [Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing](https://mlsanity.com/paper/2304.12888/) (2023)

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

- [The Paradigm Shift: A Comprehensive Survey on Large Vision Language Models for Multimodal Fake News Detection](https://mlsanity.com/paper/2601.15316/) (2026)
- [Misinformation Detection using Large Language Models with Explainability](https://mlsanity.com/paper/2510.18918/) (2025)
- [SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection](https://mlsanity.com/paper/2511.04692/) (2025)
- [Large language models for spreading dynamics in complex systems](https://mlsanity.com/paper/2602.08085/) (2026)
- [LLM-MRD: LLM-Guided Multi-View Reasoning Distillation for Fake News Detection](https://mlsanity.com/paper/2603.19293/) (2026)
- [Retrieval-Augmented Multimodal Model for Fake News Detection](https://mlsanity.com/paper/2604.18112/) (2026)
- [Let the Bullets Fly: Multimodal Fake News Detection with Temporal-Aligned Generative Danmaku](https://mlsanity.com/paper/2608.22832/) (2026)

## Abstract (arXiv)

The questionable responses caused by knowledge hallucination may lead to LLMs' unstable ability in decision-making. However, it has never been investigated whether the LLMs' hallucination is possibly usable to generate negative reasoning for facilitating the detection of fake news. This study proposes a novel supervised self-reinforced reasoning rectification approach - SR3 that yields both common reasonable reasoning and wrong understandings (negative reasoning) for news via LLMs reflection for semantic consistency learning. Upon that, we construct a negative reasoning-based news learning model called - NRFE, which leverages positive or negative news-reasoning pairs for learning the semantic consistency between them. To avoid the impact of label-implicated reasoning, we deploy a student model - NRFE-D that only takes news content as input to inspect the performance of our method by distilling the knowledge from NRFE. The experimental results verified on three popular fake news datasets demonstrate the superiority of our method compared with three kinds of baselines including prompting on LLMs, fine-tuning on pre-trained SLMs, and other representative fake news detection methods.