LexChronos: An Agentic Framework for Structured Event Timeline Extraction in Indian Jurisprudence

2026-03-02

AI Summary

This work addresses the limitations of traditional approaches that treat Indian judicial judgments as unstructured text, thereby constraining the performance of large language models in legal tasks. To overcome this, the authors propose LexChronos, a novel framework that introduces the first structured event timeline extraction method tailored to the Indian judicial system. LexChronos employs a dual-agent collaborative architecture: a LoRA-fine-tuned extraction agent and a pretrained feedback agent, leveraging synthetic data generated by DeepSeek-R1 and GPT-4 alongside a confidence-driven iterative refinement mechanism. The framework achieves a BERT-F1 score of 0.8751 on a synthetic test set and, in downstream summarization tasks, produces structured timelines that GPT-4 prefers in 75% of cases, significantly enhancing legal text comprehension and application.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

Understanding and predicting judicial outcomes demands nuanced analysis of legal documents. Traditional approaches treat judgments and proceedings as unstructured text, limiting the effectiveness of large language models (LLMs) in tasks such as summarization, argument generation, and judgment prediction. We propose LexChronos, an agentic framework that iteratively extracts structured event timelines from Supreme Court of India judgments. LexChronos employs a dual-agent architecture: a LoRA-instruct-tuned extraction agent identifies candidate events, while a pre-trained feedback agent scores and refines them through a confidence-driven loop. To address the scarcity of Indian legal event datasets, we construct a synthetic corpus of 2000 samples using reverse-engineering techniques with DeepSeek-R1 and GPT-4, generating gold-standard event annotations. Our pipeline achieves a BERT-based F1 score of 0.8751 against this synthetic ground truth. In downstream evaluations on legal text summarization, GPT-4 preferred structured timelines over unstructured baselines in 75% of cases, demonstrating improved comprehension and reasoning in Indian jurisprudence. This work lays a foundation for future legal AI applications in the Indian context, such as precedent mapping, argument synthesis, and predictive judgment modelling, by harnessing structured representations of legal events.

Problem

• structured event timeline extraction
• Indian jurisprudence
• legal document understanding
• judicial outcome prediction
• unstructured legal text

Innovation

• agentic framework
• structured event timeline extraction
• LoRA-instruct tuning
• synthetic legal corpus
• confidence-driven refinement