Recent years witnessed tremendous advancements in natural language processing (NLP) because of the development of complex language models that have automated several NLP applications, including text summarisation. Despite this progress, Malayalam text summarisation still faces challenges because of the peculiarities of the language. This research paper explores the potential of using a large language model, specifically the LLaMA (Large Language Model Meta AI) framework, for text summarisation of Malayalam language. In order to assess the performance of LLaMA for text summarization, for the low-resource language Malayalam, a dataset was curated with reference text and summaries. The evaluation showed that the LLaMA model could effectively summarize lengthy articles while maintaining important information and coherence. The generated summaries were compared with the reference summaries generated by human writers to observe how well aligned the model was with a human level of summarisation. The results proved that LLM can deal with the Malayalam text summarisation task, but more research is needed to understand the most relevant training strategy.

Figurative language, particularly in under represented languages within the Dravidian family, serves as a critical medium for conveying emotions and cultural meaning. Despite the rich literary traditions of languages such as Malayalam, Tamil, Telugu, and Kannada, there has been minimal progress in developing computational techniques to analyze figurative expressions. Historically, Malayalam was known by various names, such as Malayanma and Malabari. Similarly Kerala was known as Malanadu before adopting its current name, which metaphorically refers to the land between the Indian Ocean and the Western Ghats. In this study, we introduce the UPAMA Model(MalUpama), designed to identify Similes in Malayalam, an under-resourced Dravidian language mostly spoken in the state of southern India, Kerala. The current research focuses on detection of presence of Simile in Malayalam prose using the ‘Upama model’. This paper outlines the detection of Simile in Malayalam sentences and a detection accuracy of 94.5% is achieved by the proposed method. To the best of our knowledge this is the first work in the Malayalam language, explores computational techniques with a particular focus on applying machine learning to analyze figurative expressions which can be adopted for other Dravidian Languages too. The dataset developed for this study is made publicly available, allowing scholars to contribute and explore more on the category ‘Upama’ of Figurative Languages (‘Alankarangal’) of Malayalam language.