# A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers

arXiv: https://arxiv.org/abs/2502.04535 · HTML: https://mlsanity.com/paper/2502.04535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2025.

## Abstract (arXiv)

Length-control summarization aims to condense long texts into a short one within a certain length limit. Previous approaches often use autoregressive (AR) models and treat the length requirement as a soft constraint, which may not always be satisfied. In this study, we propose a novel length-control decoding algorithm based on the Directed Acyclic Transformer (DAT). Our approach allows for multiple plausible sequence fragments and predicts a path to connect them. In addition, we propose a Sequence Maximum a Posteriori (SeqMAP) decoding algorithm that marginalizes different possible paths and finds the most probable summary satisfying the length budget. Our algorithm is based on beam search, which further facilitates a reranker for performance improvement. Experimental results on the Gigaword and DUC2004 datasets demonstrate our state-of-the-art performance for length-control summarization.