DeLIVeR: Reinforced Knowledge Graph Exploration for Fact-Checking
DeLIVeR is a new framework that frames evidence retrieval for automated fact-checking as a reinforced strategic exploration task. It uses a Planner LLM to decompose complex claims into targeted questions, guiding traversal of structured knowledge graphs for high-precision evidence. On the LIAR, FEVER, and PolitiFact datasets, DeLIVeR achieves peak F1-scores of 83.73, 84.57, and 79.70, representing a 10-15% improvement over the HippoRAG2 baseline.
Why it matters: This work advances automated fact-checking by combining reinforcement learning with knowledge graph traversal, enabling more transparent and auditable multi-hop reasoning for misinformation detection.
Full story at: arXiv Computation and Language ↗