# Unsupervised Identification of Relevant Prior Cases

arXiv: https://arxiv.org/abs/2107.08973 · HTML: https://mlsanity.com/paper/2107.08973/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 17 references that are in the map.
- First posted on arXiv 19 Jul 2021.

## Builds on (most cited first, 2 of 2)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [IR-BERT: Leveraging BERT for Semantic Search in Background Linking for News Articles](https://mlsanity.com/paper/2007.12603/) (2020)

## Built on by (most cited first, 4 of 4)

- [U-CREAT: Unsupervised Case Retrieval using Events extrAcTion](https://mlsanity.com/paper/2307.05260/) (2023)
- [Bridging Legal Knowledge and AI: Retrieval-Augmented Generation with Vector Stores, Knowledge Graphs, and Hierarchical Non-negative Matrix Factorization](https://mlsanity.com/paper/2502.20364/) (2025)
- [GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding](https://mlsanity.com/paper/2310.14028/) (2023)
- [A Unified Multimodal Framework for Dataset Construction and Model-Based Diagnosis of Ameloblastoma](https://mlsanity.com/paper/2602.05515/) (2026)

## Abstract (arXiv)

Document retrieval has taken its role in almost all domains of knowledge understanding, including the legal domain. Precedent refers to a court decision that is considered as authority for deciding subsequent cases involving identical or similar facts or similar legal issues. In this work, we propose different unsupervised approaches to solve the task of identifying relevant precedents to a given query case. Our proposed approaches are using word embeddings like word2vec, doc2vec, and sent2vec, finding cosine similarity using TF-IDF, retrieving relevant documents using BM25 scores, using the pre-trained model and SBERT to find the most similar document, and using the product of BM25 and TF-IDF scores to find the most relevant document for a given query. We compared all the methods based on precision@10, recall@10, and MRR. Based on the comparative analysis, we found that the TF-IDF score multiplied by the BM25 score gives the best result. In this paper, we have also presented the analysis that we did to improve the BM25 score.