Researchers have developed MAGER, a novel multi-agent genetic evolution framework designed to enhance fake news detection using large language models (LLMs). This framework addresses the challenges of information overload and modality mismatch when feeding raw propagation graphs to LLMs by automatically discovering optimized meta-paths. These meta-paths compress complex graphs into informative subgraphs, enabling frozen LLMs to perform structure-aware reasoning more effectively, particularly in zero-shot and few-shot scenarios. The system also incorporates a graph in-context learning strategy to further strengthen classification and reasoning capabilities. AI
IMPACT This research could lead to more robust and data-efficient fake news detection systems by improving how LLMs interpret complex relational data.
RANK_REASON The cluster contains a research paper detailing a new framework for fake news detection using LLMs. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- graph neural network
- Hugging Face
- large language models
- MAGER
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
