# Robust Deep Reinforcement Learning for Extractive Legal Summarization

arXiv: https://arxiv.org/abs/2111.07158 · HTML: https://mlsanity.com/paper/2111.07158/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 13 Nov 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Ranking Sentences for Extractive Summarization with Reinforcement Learning](https://mlsanity.com/paper/1802.08636/) (2018)
- [Fine-tune BERT for Extractive Summarization](https://mlsanity.com/paper/1903.10318/) (2019)
- [BillSum: A Corpus for Automatic Summarization of US Legislation](https://mlsanity.com/paper/1910.00523/) (2019)
- [Fill in the BLANC: Human-free quality estimation of document summaries](https://mlsanity.com/paper/2002.09836/) (2020)
- [Multi-Reward Reinforced Summarization with Saliency and Entailment](https://mlsanity.com/paper/1804.06451/) (2018)
- [Learning to Extract Coherent Summary via Deep Reinforcement Learning](https://mlsanity.com/paper/1804.07036/) (2018)
- [Plain English Summarization of Contracts](https://mlsanity.com/paper/1906.00424/) (2019)
- [Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization](https://mlsanity.com/paper/1909.00141/) (2019)
- [Extractive Summarization using Deep Learning](https://mlsanity.com/paper/1708.04439/) (2017)
- [Automatic Text Summarization of Legal Cases: A Hybrid Approach](https://mlsanity.com/paper/1908.09119/) (2019)

## Built on by (most cited first, 10 of 10)

- [Natural Language Processing for the Legal Domain: A Survey of Tasks, Datasets, Models, and Challenges](https://mlsanity.com/paper/2410.21306/) (2024)
- [Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans](https://mlsanity.com/paper/2209.13020/) (2022)
- [Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference Feedback](https://mlsanity.com/paper/2204.05512/) (2022)
- [Legal Extractive Summarization of U.S. Court Opinions](https://mlsanity.com/paper/2305.08428/) (2023)
- [Universal Graph Continual Learning](https://mlsanity.com/paper/2308.13982/) (2023)
- [A Comprehensive Survey on Legal Summarization: Challenges and Future Directions](https://mlsanity.com/paper/2501.17830/) (2025)
- [Creation and Analysis of an International Corpus of Privacy Laws](https://mlsanity.com/paper/2206.14169/) (2022)
- [When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance](https://mlsanity.com/paper/2507.07748/) (2025)
- [Improving Document Image Understanding with Reinforcement Finetuning](https://mlsanity.com/paper/2209.12561/) (2022)
- [ReGal: A First Look at PPO-based Legal AI for Judgment Prediction and Summarization in India](https://mlsanity.com/paper/2512.18014/) (2025)

## Abstract (arXiv)

Automatic summarization of legal texts is an important and still a challenging task since legal documents are often long and complicated with unusual structures and styles. Recent advances of deep models trained end-to-end with differentiable losses can well-summarize natural text, yet when applied to legal domain, they show limited results. In this paper, we propose to use reinforcement learning to train current deep summarization models to improve their performance on the legal domain. To this end, we adopt proximal policy optimization methods and introduce novel reward functions that encourage the generation of candidate summaries satisfying both lexical and semantic criteria. We apply our method to training different summarization backbones and observe a consistent and significant performance gain across 3 public legal datasets.