FIRE: Fact-checking with Iterative Retrieval and Verification
arXiv · · Significant research
Summary
A novel agent-based framework called FIRE is introduced for fact-checking long-form text. FIRE iteratively integrates evidence retrieval and claim verification, deciding whether to provide a final answer or generate a subsequent search query. Experiments show FIRE achieves comparable performance to existing methods while reducing LLM costs by 7.6x and search costs by 16.5x.
Keywords
fact-checking · long-form text · iterative retrieval · claim verification · large language model
Get the weekly digest
Top AI stories from the GCC region, every week.