Hallucination is the last thing you need

TL;DR

This paper explores a multi-model ensemble approach to reduce hallucinations in legal AI by integrating understanding, experience, and facts, and introduces multi-length tokenization for safeguarding legal information.

Contribution

It proposes a novel ensemble of three independent LLMs focused on understanding, experience, and facts to mitigate hallucination in legal AI applications.

Findings

Ensemble approach reduces hallucination in legal AI models

Multi-length tokenization protects key legal information

Evaluation of state-of-the-art models reveals insights into hallucination issues

Abstract

The legal profession necessitates a multidimensional approach that involves synthesizing an in-depth comprehension of a legal issue with insightful commentary based on personal experience, combined with a comprehensive understanding of pertinent legislation, regulation, and case law, in order to deliver an informed legal solution. The present offering with generative AI presents major obstacles in replicating this, as current models struggle to integrate and navigate such a complex interplay of understanding, experience, and fact-checking procedures. It is noteworthy that where generative AI outputs understanding and experience, which reflect the aggregate of various subjective views on similar topics, this often deflects the model's attention from the crucial legal facts, thereby resulting in hallucination. Hence, this paper delves into the feasibility of three independent LLMs, each focused on understanding, experience, and facts, synthesising as one single ensemble model to effectively counteract the current challenges posed by the existing monolithic generative AI models. We introduce an idea of mutli-length tokenisation to protect key information assets like common law judgements, and finally we interrogate the most advanced publicly available models for legal hallucination, with some interesting results.