A Tree-of-Thoughts Inspired Hybrid Approach for Legal Case Judgement Summarization using LLMs
For legal professionals needing concise case summaries, this work offers a novel prompting strategy that improves summarization quality over existing LLM-based methods.
The paper proposes a tree-of-thoughts inspired hybrid extractive-abstractive summarization approach for legal case judgements using LLMs. Experiments with DeepSeek and LLama show that the hybrid prompt yields better summaries than purely extractive or abstractive prompts.
In recent times, Large Language Models (LLMs) are increasingly being used for legal case judgement summarization. Most prior works have tried traditional extractive and abstractive summarization of case judgements. However, hybrid or extractive-abstractive techniques have not been explored much. In this work, we propose a novel tree-of-thoughts inspired extractive-abstractive summarization approach for legal judgement summarization. We conduct experiments using two popular LLMs, DeepSeek and LLama, and compare among extractive, abstractive and extractive-abstractive summarization. Our experiments show that the proposed extractive-abstractive prompt provides better summaries compared to other types of LLM prompts.