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

TL;DR

LexChronos introduces an agentic framework that extracts structured event timelines from Indian Supreme Court judgments, improving legal document understanding and supporting advanced legal AI applications.

Contribution

It presents a novel dual-agent architecture for iterative event extraction and constructs a synthetic dataset for Indian legal texts, enhancing timeline accuracy and downstream legal tasks.

Findings

Achieved a BERT-based F1 score of 0.8751 on synthetic data.

GPT-4 preferred structured timelines in 75% of summarization cases.

Demonstrated improved comprehension and reasoning with structured event timelines.

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.