Fact or Fiction? Improving Fact Verification with Knowledge Graphs through Simplified Subgraph Retrievals
This addresses misinformation spread by improving automated fact-checking efficiency, though it appears incremental as it optimizes an existing pipeline rather than introducing a new paradigm.
The paper tackles fact verification by simplifying evidence retrieval from knowledge graphs, replacing fine-tuned language models with simple logical retrievals. This approach reduces computational resources and improves test-set accuracy on the FactKG dataset.
Despite recent success in natural language processing (NLP), fact verification still remains a difficult task. Due to misinformation spreading increasingly fast, attention has been directed towards automatically verifying the correctness of claims. In the domain of NLP, this is usually done by training supervised machine learning models to verify claims by utilizing evidence from trustworthy corpora. We present efficient methods for verifying claims on a dataset where the evidence is in the form of structured knowledge graphs. We use the FactKG dataset, which is constructed from the DBpedia knowledge graph extracted from Wikipedia. By simplifying the evidence retrieval process, from fine-tuned language models to simple logical retrievals, we are able to construct models that both require less computational resources and achieve better test-set accuracy.