# A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection

arXiv: https://arxiv.org/abs/2508.19633 · HTML: https://mlsanity.com/paper/2508.19633/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 27 Aug 2025.

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

- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [FakeNewsNet: A Data Repository with News Content, Social Context and Spatialtemporal Information for Studying Fake News on Social Media](https://mlsanity.com/paper/1809.01286/) (2018)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [Symbolic Learning Enables Self-Evolving Agents](https://mlsanity.com/paper/2406.18532/) (2024)
- [Fake News in Sheep's Clothing: Robust Fake News Detection Against LLM-Empowered Style Attacks](https://mlsanity.com/paper/2310.10830/) (2023)
- [MDFEND: Multi-domain Fake News Detection](https://mlsanity.com/paper/2201.00987/) (2022)
- [From Skepticism to Acceptance: Simulating the Attitude Dynamics Toward Fake News](https://mlsanity.com/paper/2403.09498/) (2024)
- [False Information on Web and Social Media: A Survey](https://mlsanity.com/paper/1804.08559/) (2018)
- [Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges](https://mlsanity.com/paper/2403.18249/) (2024)
- [Fact-Enhanced Synthetic News Generation](https://mlsanity.com/paper/2012.04778/) (2020)
- [RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agents](https://mlsanity.com/paper/2406.11132/) (2024)
- [How does Truth Evolve into Fake News? An Empirical Study of Fake News Evolution](https://mlsanity.com/paper/2103.05944/) (2021)
- [Fake News Detection: Experiments and Approaches beyond Linguistic Features](https://mlsanity.com/paper/2109.12914/) (2021)

## Built on by (most cited first, 3 of 3)

- [MetaResearcher: Scaling Deep Research via Self-Reflective Reinforcement Learning in Adversarial Virtual Environments](https://mlsanity.com/paper/2606.19893/) (2026)
- [DIVER: Dynamic Iterative Visual Evidence Reasoning for Multimodal Fake News Detection](https://mlsanity.com/paper/2601.07178/) (2026)
- [Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models](https://mlsanity.com/paper/2608.18884/) (2026)

## Abstract (arXiv)

Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation. Previous detection methods, including fine-tuned small models or LLM-based detectors, often struggle with its dynamically evolving nature. In this work, we propose a novel framework called the Symbolic Adversarial Learning Framework (SALF), which implements an adversarial training paradigm by an agent symbolic learning optimization process, rather than relying on numerical updates. SALF introduces a paradigm where the generation agent crafts deceptive narratives, and the detection agent uses structured debates to identify logical and factual flaws for detection, and they iteratively refine themselves through such adversarial interactions. Unlike traditional neural updates, we represent agents using agent symbolic learning, where learnable weights are defined by agent prompts, and simulate back-propagation and gradient descent by operating on natural language representations of weights, loss, and gradients. Experiments on two multilingual benchmark datasets demonstrate SALF's effectiveness, showing it generates sophisticated fake news that degrades state-of-the-art detection performance by up to 53.4% in Chinese and 34.2% in English on average. SALF also refines detectors, improving detection of refined content by up to 7.7%. We hope our work inspires further exploration into more robust, adaptable fake news detection systems.