# Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization

Source: [Domain Aligned Prefix Averaging for Domain Generalization in Abstractive Summarization](<https://www.sota2.com/research/paper/68fa6f771e209131cea45c57>)

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

Data updated: 2026-01-02T02:38:41.174Z

Authors: Pranav Ajit Nair, Sukomal Pal, Pradeepika Verma

Published: 2023-05-26T11:02:38.000Z

## Abstract

Domain generalization is hitherto an underexplored area applied in abstractive summarization. Moreover, most existing works on domain generalization have sophisticated training algorithms. In this paper, we propose a lightweight, weight averaging based, Domain Aligned Prefix Averaging approach to domain generalization for abstractive summarization. Given a number of source domains, our method first trains a prefix for each one of them. These source prefixes generate summaries for a small number of target domain documents. The similarity of the generated summaries to their corresponding documents is used for calculating weights required to average source prefixes. In DAPA, prefix tuning allows for lightweight finetuning, and weight averaging allows for the computationally efficient addition of new source domains. When evaluated on four diverse summarization domains, DAPA shows comparable or better performance against the baselines, demonstrating the effectiveness of its prefix averaging scheme.

## 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.

- [Text Summarization on News (test)](<https://www.sota2.com/research/sota/text-summarization-on-news-test.md>): Text Summarization; News (test); ROUGE-1: 40.28.

- [Text Summarization on Chat (test)](<https://www.sota2.com/research/sota/text-summarization-on-chat-test.md>): Text Summarization; Chat (test); ROUGE-1: 28.23.

- [Text Summarization on Scientific (test)](<https://www.sota2.com/research/sota/text-summarization-on-scientific-test.md>): Text Summarization; Scientific (test); ROUGE-1: 30.84.

- [Text Summarization on Social-media (test)](<https://www.sota2.com/research/sota/text-summarization-on-social-media-test.md>): Text Summarization; Social-media (test); ROUGE-1: 16.97.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2305.16820>)

[PDF](<https://arxiv.org/pdf/2305.16820.pdf>)

[Implementation](<https://github.com/pranavajitnair/DAPA>)