Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies

TL;DR

This paper introduces a retrieval-based data augmentation method using ensemble retrievers and multiple language models to improve question answering on privacy policy documents, significantly boosting performance.

Contribution

It presents a novel data augmentation framework that combines ensemble retrievers and multiple LMs to enhance QA datasets for privacy policies, achieving state-of-the-art results.

Findings

Achieved a 10% F1 score improvement on PrivacyQA benchmark.

Established a new state-of-the-art F1 score of 50%.

Demonstrated the effectiveness of ensemble retrievers and multi-LM augmentation.

Abstract

Prior studies in privacy policies frame the question answering (QA) task as identifying the most relevant text segment or a list of sentences from a policy document given a user query. Existing labeled datasets are heavily imbalanced (only a few relevant segments), limiting the QA performance in this domain. In this paper, we develop a data augmentation framework based on ensembling retriever models that captures the relevant text segments from unlabeled policy documents and expand the positive examples in the training set. In addition, to improve the diversity and quality of the augmented data, we leverage multiple pre-trained language models (LMs) and cascade them with noise reduction filter models. Using our augmented data on the PrivacyQA benchmark, we elevate the existing baseline by a large margin (10\% F1) and achieve a new state-of-the-art F1 score of 50\%. Our ablation studies provide further insights into the effectiveness of our approach.