# LegalSeg: Unlocking the Structure of Indian Legal Judgments Through Rhetorical Role Classification

arXiv: https://arxiv.org/abs/2502.05836 · HTML: https://mlsanity.com/paper/2502.05836/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 9 Feb 2025.

## Builds on (most cited first, 12 of 12)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation](https://mlsanity.com/paper/2105.13562/) (2021)
- [Identification of Rhetorical Roles of Sentences in Indian Legal Judgments](https://mlsanity.com/paper/1911.05405/) (2019)
- [Pre-trained Language Models for the Legal Domain: A Case Study on Indian Law](https://mlsanity.com/paper/2209.06049/) (2022)
- [Semantic Segmentation of Legal Documents via Rhetorical Roles](https://mlsanity.com/paper/2112.01836/) (2021)
- [Corpus for Automatic Structuring of Legal Documents](https://mlsanity.com/paper/2201.13125/) (2022)
- [Legal Judgment Reimagined: PredEx and the Rise of Intelligent AI Interpretation in Indian Courts](https://mlsanity.com/paper/2406.04136/) (2024)
- [Legal Question-Answering in the Indian Context: Efficacy, Challenges, and Potential of Modern AI Models](https://mlsanity.com/paper/2309.14735/) (2023)
- [nigam@COLIEE-22: Legal Case Retrieval and Entailment using Cascading of Lexical and Semantic-based models](https://mlsanity.com/paper/2204.07853/) (2022)
- [Nonet at SemEval-2023 Task 6: Methodologies for Legal Evaluation](https://mlsanity.com/paper/2310.11049/) (2023)
- [SemEval 2023 Task 6: LegalEval - Understanding Legal Texts](https://mlsanity.com/paper/2304.09548/) (2023)
- [HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents](https://mlsanity.com/paper/2409.18647/) (2024)

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

- [NyayaRAG: Realistic Legal Judgment Prediction with RAG under the Indian Common Law System](https://mlsanity.com/paper/2508.00709/) (2025)
- [TathyaNyaya and FactLegalLlama: Advancing Factual Judgment Prediction and Explanation in the Indian Legal Context](https://mlsanity.com/paper/2504.04737/) (2025)
- [Segment First, Retrieve Better: Realistic Legal Search via Rhetorical Role-Based Queries](https://mlsanity.com/paper/2508.00679/) (2025)
- [Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling](https://mlsanity.com/paper/2603.03856/) (2026)
- [IBPS: Indian Bail Prediction System](https://mlsanity.com/paper/2508.07592/) (2025)
- [NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System](https://mlsanity.com/paper/2604.09069/) (2026)
- [HKJudge: A Legal Discourse-Annotated Corpus for Interpreting What Courts Find, How They Reason, and What They Rule](https://mlsanity.com/paper/2606.06679/) (2026)
- [Mining Legal Arguments in U.S. Corporate Case Law](https://mlsanity.com/paper/2609.25441/) (2026)

## Abstract (arXiv)

In this paper, we address the task of semantic segmentation of legal documents through rhetorical role classification, with a focus on Indian legal judgments. We introduce LegalSeg, the largest annotated dataset for this task, comprising over 7,000 documents and 1.4 million sentences, labeled with 7 rhetorical roles. To benchmark performance, we evaluate multiple state-of-the-art models, including Hierarchical BiLSTM-CRF, TransformerOverInLegalBERT (ToInLegalBERT), Graph Neural Networks (GNNs), and Role-Aware Transformers, alongside an exploratory RhetoricLLaMA, an instruction-tuned large language model. Our results demonstrate that models incorporating broader context, structural relationships, and sequential sentence information outperform those relying solely on sentence-level features. Additionally, we conducted experiments using surrounding context and predicted or actual labels of neighboring sentences to assess their impact on classification accuracy. Despite these advancements, challenges persist in distinguishing between closely related roles and addressing class imbalance. Our work underscores the potential of advanced techniques for improving legal document understanding and sets a strong foundation for future research in legal NLP.