We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 \emph{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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2502.04535")
get_code_for_paper("2502.04535")
have("2502.04535")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2502.04535.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2502.04535)
Connect an agent — have() is free.