Poster
in
Workshop: 2nd Workshop on Generative AI and Law (GenLaw ’24)
GROG: Reducing LLM Hallucinations for Improved Legal Reasoning
Daniel McNeela
Abstract:
In this work we introduce Graph Retrieval-Optimized Generation (GROG), a method for reducing LLM hallucinations in contexts where external, graph-structured knowledge is available. We test our method on retrieval and generation tasks conditioned on publicly-available USPTO patent data and show promising results, suggesting that this method warrants further study in more diverse legal contexts and downstream applications.
Chat is not available.