# Global-aware Beam Search for Neural Abstractive Summarization

arXiv: https://arxiv.org/abs/2009.06891 · HTML: https://mlsanity.com/paper/2009.06891/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Sep 2020.

## Built on by (most cited first, 8 of 8)

- [Revisiting the Gold Standard: Grounding Summarization Evaluation with Robust Human Evaluation](https://mlsanity.com/paper/2212.07981/) (2022)
- [More Interpretable Graph Similarity Computation via Maximum Common Subgraph Inference](https://mlsanity.com/paper/2208.04580/) (2022)
- [RCsearcher: Reaction Center Identification in Retrosynthesis via Deep Q-Learning](https://mlsanity.com/paper/2301.12071/) (2023)
- [Sub-GMN: The Neural Subgraph Matching Network Model](https://mlsanity.com/paper/2104.00186/) (2021)
- [Towards Transparent AI: A Survey on Explainable Language Models](https://mlsanity.com/paper/2509.21631/) (2025)
- [Retrosynthesis Prediction via Search in (Hyper) Graph](https://mlsanity.com/paper/2402.06772/) (2024)
- [A Semi-Autoregressive Graph Generative Model for Dependency Graph Parsing](https://mlsanity.com/paper/2306.12018/) (2023)
- [Use neural networks to recognize students' handwritten letters and incorrect symbols](https://mlsanity.com/paper/2309.06221/) (2023)

## Abstract (arXiv)

This study develops a calibrated beam-based algorithm with awareness of the global attention distribution for neural abstractive summarization, aiming to improve the local optimality problem of the original beam search in a rigorous way. Specifically, a novel global protocol is proposed based on the attention distribution to stipulate how a global optimal hypothesis should attend to the source. A global scoring mechanism is then developed to regulate beam search to generate summaries in a near-global optimal fashion. This novel design enjoys a distinctive property, i.e., the global attention distribution could be predicted before inference, enabling step-wise improvements on the beam search through the global scoring mechanism. Extensive experiments on nine datasets show that the global (attention)-aware inference significantly improves state-of-the-art summarization models even using empirical hyper-parameters. The algorithm is also proven robust as it remains to generate meaningful texts with corrupted attention distributions. The codes and a comprehensive set of examples are available.