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.

DAPA, the Digital Asset Policy Alliance, is launching as a collaborative initiative focused on the public policy implications of web3 with initial participants from Fabric Ventures, the web3 venture contributor, Coadec, The Coalition for a Digital Economy, Project Vellir, NEAR Protocol and Unstoppable Finance. DAPA welcomes other volunteers and will progressively decentralise with'community-driven' at its heart with the upcoming DAPA DAO. DAPA's mission is to improve understanding of web3 and crypto technology and ensure that new industry regulation protects consumers and businesses, while also promoting innovation and adoption of the transformative benefits of this new technology. Decentralisation technology has the potential to transform our society for the better. There has been rapid growth in blockchain technology and consumer demand for web3 applications, which has attracted the attention of policy makers and regulators, including in the UK, EU and US.