English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Automatic summarization of legal case judgements has traditionally beenattempted by using extractive summarization methods. However, in recent years,abstractive summarization models are gaining popularity since they can generatemore natural and coherent summaries. Legal domain-specific pre-trainedabstractive summarization models are now available. Moreover, general-domainpre-trained Large Language Models (LLMs), such as ChatGPT, are known togenerate high-quality text and have the capacity for text summarization. Henceit is natural to ask if these models are ready for off-the-shelf application toautomatically generate abstractive summaries for case judgements. To explorethis question, we apply several state-of-the-art domain-specific abstractivesummarization models and general-domain LLMs on Indian court case judgements,and check the quality of the generated summaries. In addition to standardmetrics for summary quality, we check for inconsistencies and hallucinations inthe summaries. We see that abstractive summarization models generally achieveslightly higher scores than extractive models in terms of standard summaryevaluation metrics such as ROUGE and BLEU. However, we often find inconsistentor hallucinated information in the generated abstractive summaries. Overall,our investigation indicates that the pre-trained abstractive summarizationmodels and LLMs are not yet ready for fully automatic deployment for casejudgement summarization; rather a human-in-the-loop approach including manualchecks for inconsistencies is more suitable at present.

How Ready are Pre-trained Abstractive Models and LLMs for Legal Case Judgement Summarization?