# Learning Fine-grained Fact-Article Correspondence in Legal Cases arXiv: https://arxiv.org/abs/2104.10726 ยท HTML: https://mlsanity.com/paper/2104.10726/ ## Key facts - Cited by 15 papers in the map (data through 14 Oct 2026). - Builds on 24 of its 55 references that are in the map. - First posted on arXiv 21 Apr 2021. ## Builds on (most cited first, 24 of 24) - [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) - [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013) - [Neural Legal Judgment Prediction in English](https://mlsanity.com/paper/1906.02059/) (2019) - [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018) - [A Deep Relevance Matching Model for Ad-hoc Retrieval](https://mlsanity.com/paper/1711.08611/) (2017) - [Convolutional Neural Network Architectures for Matching Natural Language Sentences](https://mlsanity.com/paper/1503.03244/) (2015) - [Distinguish Confusing Law Articles for Legal Judgment Prediction](https://mlsanity.com/paper/2004.02557/) (2020) - [Learning to Predict Charges for Criminal Cases with Legal Basis](https://mlsanity.com/paper/1707.09168/) (2017) - [Text Matching as Image Recognition](https://mlsanity.com/paper/1602.06359/) (2016) - [Legal Judgment Prediction via Multi-Perspective Bi-Feedback Network](https://mlsanity.com/paper/1905.03969/) (2019) - [Neural Natural Language Inference Models Enhanced with External Knowledge](https://mlsanity.com/paper/1711.04289/) (2017) - [A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations](https://mlsanity.com/paper/1511.08277/) (2015) - [Attention-over-Attention Neural Networks for Reading Comprehension](https://mlsanity.com/paper/1607.04423/) (2016) - [Simple and Effective Text Matching with Richer Alignment Features](https://mlsanity.com/paper/1908.00300/) (2019) - [Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence](https://mlsanity.com/paper/2005.01096/) (2020) - [Neural Data-to-Text Generation with LM-based Text Augmentation](https://mlsanity.com/paper/2102.03556/) (2021) - [Diversifying Dialogue Generation with Non-Conversational Text](https://mlsanity.com/paper/2005.04346/) (2020) - [MatchZoo: A Learning, Practicing, and Developing System for Neural Text Matching](https://mlsanity.com/paper/1905.10289/) (2019) - [DART: A Lightweight Quality-Suggestive Data-to-Text Annotation Tool](https://mlsanity.com/paper/2010.04141/) (2020) - [Select and Attend: Towards Controllable Content Selection in Text Generation](https://mlsanity.com/paper/1909.04453/) (2019) - [NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation](https://mlsanity.com/paper/1810.00671/) (2018) - [Unsupervised Pidgin Text Generation By Pivoting English Data and Self-Training](https://mlsanity.com/paper/2003.08272/) (2020) - [Knowledge Enhanced Hybrid Neural Network for Text Matching](https://mlsanity.com/paper/1611.04684/) (2016) ## Built on by (most cited first, 15 of 15) - [LawBench: Benchmarking Legal Knowledge of Large Language Models](https://mlsanity.com/paper/2309.16289/) (2023) - [A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges](https://mlsanity.com/paper/2204.04859/) (2022) - [Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction](https://mlsanity.com/paper/2502.06882/) (2025) - [ClassActionPrediction: A Challenging Benchmark for Legal Judgment Prediction of Class Action Cases in the US](https://mlsanity.com/paper/2211.00582/) (2022) - [CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding](https://mlsanity.com/paper/2305.05393/) (2023) - [Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/2112.06370/) (2021) - [LAiW: A Chinese Legal Large Language Models Benchmark](https://mlsanity.com/paper/2310.05620/) (2023) - [PILOT: Legal Case Outcome Prediction with Case Law](https://mlsanity.com/paper/2401.15770/) (2024) - [LegiLM: A Fine-Tuned Legal Language Model for Data Compliance](https://mlsanity.com/paper/2409.13721/) (2024) - [InternLM-Law: An Open Source Chinese Legal Large Language Model](https://mlsanity.com/paper/2406.14887/) (2024) - [Unsupervised Simplification of Legal Texts](https://mlsanity.com/paper/2209.00557/) (2022) - [When Large Language Models Meet Law: Dual-Lens Taxonomy, Technical Advances, and Ethical Governance](https://mlsanity.com/paper/2507.07748/) (2025) - [SEMDR: A Semantic-Aware Dual Encoder Model for Legal Judgment Prediction with Legal Clue Tracing](https://mlsanity.com/paper/2408.09717/) (2024) - [BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Prediction](https://mlsanity.com/paper/2404.10481/) (2024) - [Incorporating Legal Logic into Deep Learning: An Intelligent Approach to Probation Prediction](https://mlsanity.com/paper/2508.12286/) (2025) ## Abstract (arXiv) Automatically recommending relevant law articles to a given legal case has attracted much attention as it can greatly release human labor from searching over the large database of laws. However, current researches only support coarse-grained recommendation where all relevant articles are predicted as a whole without explaining which specific fact each article is relevant with. Since one case can be formed of many supporting facts, traversing over them to verify the correctness of recommendation results can be time-consuming. We believe that learning fine-grained correspondence between each single fact and law articles is crucial for an accurate and trustworthy AI system. With this motivation, we perform a pioneering study and create a corpus with manually annotated fact-article correspondences. We treat the learning as a text matching task and propose a multi-level matching network to address it. To help the model better digest the content of law articles, we parse articles in form of premise-conclusion pairs with random forest. Experiments show that the parsed form yielded better performance and the resulting model surpassed other popular text matching baselines. Furthermore, we compare with previous researches and find that establishing the fine-grained fact-article correspondences can improve the recommendation accuracy by a large margin. Our best system reaches an F1 score of 96.3%, making it of great potential for practical use. It can also significantly boost the downstream task of legal decision prediction, increasing the F1 score by up to 12.7%.