# MACSum: Controllable Summarization with Mixed Attributes

Source: [MACSum: Controllable Summarization with Mixed Attributes](<https://www.sota2.com/research/paper/68fa6fa51e209131cea46e0e>)

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

Data updated: 2025-10-26T01:24:25.039Z

Authors: Yusen Zhang, Yang Liu, Ziyi Yang, Yuwei Fang, Yulong Chen, Dragomir Radev, Chenguang Zhu, Michael Zeng, Rui Zhang

Published: 2022-11-09T17:17:37.000Z

## Abstract

Controllable summarization allows users to generate customized summaries with specified attributes. However, due to the lack of designated annotations of controlled summaries, existing works have to craft pseudo datasets by adapting generic summarization benchmarks. Furthermore, most research focuses on controlling single attributes individually (e.g., a short summary or a highly abstractive summary) rather than controlling a mix of attributes together (e.g., a short and highly abstractive summary). In this paper, we propose MACSum, the first human-annotated summarization dataset for controlling mixed attributes. It contains source texts from two domains, news articles and dialogues, with human-annotated summaries controlled by five designed attributes (Length, Extractiveness, Specificity, Topic, and Speaker). We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization based on hard prompt tuning and soft prefix tuning. Results and analysis demonstrate that hard prompt models yield the best performance on all metrics and human evaluations. However, mixed-attribute control is still challenging for summarization tasks. Our dataset and code are available at https://github.com/psunlpgroup/MACSum.

## 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.

- [Controllable Summarization on MACSumDoc](<https://www.sota2.com/research/sota/controllable-summarization-on-macsumdoc.md>): Controllable Summarization; MACSumDoc; Ext Score: 9.04.

- [Controllable Summarization on MACSumDial](<https://www.sota2.com/research/sota/controllable-summarization-on-macsumdial.md>): Controllable Summarization; MACSumDial; Ext Score: 6.66.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2211.05041>)

[PDF](<https://arxiv.org/pdf/2211.05041.pdf>)
