A Search for Prompts: Generating Structured Answers from Contracts
This addresses automating legal question answering for contracts, but it is incremental as it builds on existing LLM methods with specific optimizations.
The paper tackled the problem of generating structured answers from legal contracts to automate human review, finding that their prompt templates for GPT-3.5-Turbo were far more accurate than semantic matching approaches, with further improvements through tweaks and in-context learning.
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.