# BanditSum: Extractive Summarization as a Contextual Bandit

arXiv: https://arxiv.org/abs/1809.09672 · HTML: https://mlsanity.com/paper/1809.09672/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2018.

## Built on by (most cited first, 30 of 46)

- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Robustness Gym: Unifying the NLP Evaluation Landscape](https://mlsanity.com/paper/2101.04840/) (2021)
- [Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors](https://mlsanity.com/paper/2205.12854/) (2022)
- [Large Language Models are Not Yet Human-Level Evaluators for Abstractive Summarization](https://mlsanity.com/paper/2305.13091/) (2023)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [Discrete Prompt Compression with Reinforcement Learning](https://mlsanity.com/paper/2308.08758/) (2023)
- [Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand](https://mlsanity.com/paper/2112.04139/) (2021)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [Document-Level Text Simplification: Dataset, Criteria and Baseline](https://mlsanity.com/paper/2110.05071/) (2021)
- [Spurious Correlations in Reference-Free Evaluation of Text Generation](https://mlsanity.com/paper/2204.09890/) (2022)
- [RefSum: Refactoring Neural Summarization](https://mlsanity.com/paper/2104.07210/) (2021)
- [MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes](https://mlsanity.com/paper/2107.08929/) (2021)
- [Multiplex Graph Neural Network for Extractive Text Summarization](https://mlsanity.com/paper/2108.12870/) (2021)
- [Topic-Guided Abstractive Multi-Document Summarization](https://mlsanity.com/paper/2110.11207/) (2021)
- [Efficient Unsupervised Sentence Compression by Fine-tuning Transformers with Reinforcement Learning](https://mlsanity.com/paper/2205.08221/) (2022)
- [How well do you know your summarization datasets?](https://mlsanity.com/paper/2106.11388/) (2021)
- [NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist](https://mlsanity.com/paper/2305.08566/) (2023)
- [StreamHover: Livestream Transcript Summarization and Annotation](https://mlsanity.com/paper/2109.05160/) (2021)
- [A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization](https://mlsanity.com/paper/2205.14522/) (2022)
- [Question-aware Transformer Models for Consumer Health Question Summarization](https://mlsanity.com/paper/2106.00219/) (2021)
- [TLDR9+: A Large Scale Resource for Extreme Summarization of Social Media Posts](https://mlsanity.com/paper/2110.01159/) (2021)
- [SlideSpawn: An Automatic Slides Generation System for Research Publications](https://mlsanity.com/paper/2411.17719/) (2024)
- [EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents](https://mlsanity.com/paper/2606.05894/) (2026)
- [Inverse Reinforcement Learning for Text Summarization](https://mlsanity.com/paper/2212.09917/) (2022)
- [Multi-Perspective Abstractive Answer Summarization](https://mlsanity.com/paper/2104.08536/) (2021)
- [Summary Explorer: Visualizing the State of the Art in Text Summarization](https://mlsanity.com/paper/2108.01879/) (2021)
- [Towards Interactive Language Modeling](https://mlsanity.com/paper/2112.11911/) (2021)
- [EDU-level Extractive Summarization with Varying Summary Lengths](https://mlsanity.com/paper/2210.04029/) (2022)
- [CoPERLex: Content Planning with Event-based Representations for Legal Case Summarization](https://mlsanity.com/paper/2501.14112/) (2025)

## Abstract (arXiv)

In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstrating that BanditSum is able to achieve ROUGE scores that are better than or comparable to the state-of-the-art for extractive summarization, and converges using significantly fewer update steps than competing approaches. In addition, we show empirically that BanditSum performs significantly better than competing approaches when good summary sentences appear late in the source document.