# MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering

Source: [MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering](<https://www.sota2.com/research/paper/68fa70d51e209131cea4d878>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:51:52.116Z

Authors: Nianlong Gu, Yingqiang Gao, Richard H. R. Hahnloser

Published: 2023-10-10T09:06:08.000Z

## Abstract

We introduce MemSum-DQA, an efficient system for document question answering (DQA) that leverages MemSum, a long document extractive summarizer. By prefixing each text block in the parsed document with the provided question and question type, MemSum-DQA selectively extracts text blocks as answers from documents. On full-document answering tasks, this approach yields a 9% improvement in exact match accuracy over prior state-of-the-art baselines. Notably, MemSum-DQA excels in addressing questions related to child-relationship understanding, underscoring the potential of extractive summarization techniques for DQA tasks.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2310.06436>)

[PDF](<https://arxiv.org/pdf/2310.06436.pdf>)