Evaluating Generative Patent Language Models

TL;DR

This paper develops and evaluates patent-specific generative language models using a novel keystroke-saving metric, revealing that larger models are not always more effective for human-centric autocompletion tasks.

Contribution

It introduces a keystroke-based evaluation metric for patent language models and demonstrates that smaller models can outperform larger ones in human-centric tasks.

Findings

Largest model (6B parameters) is not always the best for keystroke savings.

Keystroke-based metric differs from traditional token-based metrics.

Pre-trained patent language models are released for future research.

Abstract

Generative language models are promising for assisting human writing in various domains. This manuscript aims to build generative language models in the patent domain and evaluate model performance from a human-centric perspective. The perspective is to measure the ratio of keystrokes that can be saved by autocompletion based on generative patent language models. A higher ratio means a more effective model which can save more keystrokes. This metric can be used to benchmark model performance. The metric is different from conventional machine-centric metrics that are token-based instead of keystroke-based. In terms of model size, the largest model built in this manuscript is 6B, which is state-of-the-art in the patent domain. Based on the metric, it is found that the largest model is not necessarily the best for the human-centric metric. The finding means that keeping increasing model sizes in the patent domain might be unnecessary if the purpose is to assist human writing with autocompletion. Several patent language models are pre-trained from scratch in this research. The pre-trained models are released for future researchers. Several visualization tools are also provided. The importance of building a generative language model in the patent domain is the potential to facilitate creativity and innovations in the future.