A Search for Prompts: Generating Structured Answers from Contracts

TL;DR

This paper explores prompt engineering for legal question answering using GPT-3.5-Turbo, demonstrating that well-designed prompts outperform semantic matching in accuracy for extracting structured answers from contracts.

Contribution

It introduces a prompt-based approach for legal QA that improves accuracy over semantic matching and discusses methods to enhance reliability and performance.

Findings

Prompt templates significantly outperform semantic matching in accuracy.

In-context learning improves the performance and reliability of prompt-based legal QA.

Prompt tweaks and in-context learning enhance structured answer extraction.

Abstract

In many legal processes being able to action on the concrete implication of a legal question can be valuable to automating human review or signalling certain conditions (e.g., alerts around automatic renewal). To support such tasks, we present a form of legal question answering that seeks to return one (or more) fixed answers for a question about a contract clause. After showing that unstructured generative question answering can have questionable outcomes for such a task, we discuss our exploration methodology for legal question answering prompts using OpenAI's \textit{GPT-3.5-Turbo} and provide a summary of insights. Using insights gleaned from our qualitative experiences, we compare our proposed template prompts against a common semantic matching approach and find that our prompt templates are far more accurate despite being less reliable in the exact response return. With some additional tweaks to prompts and the use of in-context learning, we are able to further improve the performance of our proposed strategy while maximizing the reliability of responses as best we can.