The Factuality of Large Language Models in the Legal Domain
It addresses the reliability of LLMs for legal professionals by improving factual accuracy, though it is incremental as it builds on existing methods.
This paper tackles the problem of factuality in large language models (LLMs) when used as knowledge bases in the legal domain, finding that strategies like alias and fuzzy matching, abstaining, and additional pre-training improve performance, with precision increasing from 63% to 81% after legal pre-training.
This paper investigates the factuality of large language models (LLMs) as knowledge bases in the legal domain, in a realistic usage scenario: we allow for acceptable variations in the answer, and let the model abstain from answering when uncertain. First, we design a dataset of diverse factual questions about case law and legislation. We then use the dataset to evaluate several LLMs under different evaluation methods, including exact, alias, and fuzzy matching. Our results show that the performance improves significantly under the alias and fuzzy matching methods. Further, we explore the impact of abstaining and in-context examples, finding that both strategies enhance precision. Finally, we demonstrate that additional pre-training on legal documents, as seen with SaulLM, further improves factual precision from 63% to 81%.