LLMs -- the Good, the Bad or the Indispensable?: A Use Case on Legal Statute Prediction and Legal Judgment Prediction on Indian Court Cases

Shaurya Vats, Atharva Zope, Somsubhra De, Anurag Sharma, Upal Bhattacharya, Shubham Kumar Nigam, Shouvik Kumar Guha, Koustav Rudra, Kripabandhu Ghosh

Submission Type: Regular Short Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: NLP Applications

Keywords: Legal judgement prediction, Legal Statute prediction, LLMs, explainability, bias, fairness, ethics

Abstract: The Large Language Models (LLMs) have impacted many real-life tasks. To examine the efficacy of LLMs in a high-stake domain like law, we have applied state-of-the-art LLMs for two popular tasks: Statute Prediction and Judgment Prediction, on Indian Supreme Court cases. We see that while LLMs exhibit excellent predictive performance in Statute Prediction, their performance dips in Judgment Prediction when compared with many standard models. The explanations generated by LLMs (along with prediction) are of moderate to decent quality. We also see evidence of gender and religious bias in the LLM-predicted results. In addition, we present a note from a senior legal expert on the ethical concerns of deploying LLMs in these critical legal tasks.

Submission Number: 311