CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering

Autor: Wiratunga, Nirmalie, Abeyratne, Ramitha, Jayawardena, Lasal, Martin, Kyle, Massie, Stewart, Nkisi-Orji, Ikechukwu, Weerasinghe, Ruvan, Liret, Anne, Fleisch, Bruno

Retrieval-Augmented Generation (RAG) enhances Large Language Model (LLM) output by providing prior knowledge as context to input. This is beneficial for knowledge-intensive and expert reliant tasks, including legal question-answering, which require e

Externí odkaz: http://arxiv.org/abs/2404.04302

Grammatical Structure Oriented Automated Approach for Surface Knowledge Extraction from Open Domain Unstructured Text.

Autor: Tissera, Muditha, Weerasinghe, Ruvan

Publikováno v: Journal of Information & Communication Convergence Engineering; Jun2022, Vol. 20 Issue 2, p113-124, 12p

Statistical Machine Translation from and into Morphologically Rich and Low Resourced Languages.

Autor: Pushpananda, Randil, Weerasinghe, Ruvan, Niranjan, Mahesan

Publikováno v: Computational Linguistics & Intelligent Text Processing 16th International Conference, CICLing 2015, Cairo, Egypt, April 14-20, 2015, Proceedings, Part I; 2015, p545-556, 12p

A unified framework for reviewer reputation estimation in online review systems.

Autor: Kariyawasam, Sandunika, Weerasinghe, Ruvan

Publikováno v: 2015 IEEE 10th International Conference on Industrial & Information Systems (ICIIS); 1/1/2015, p407-412, 6p

Developing a commercial grade Tamil OCR for recognizing font and size independent text.

Autor: Liyanage, Chamila, Nadungodage, Thilini, Weerasinghe, Ruvan

Publikováno v: 2015 Fifteenth International Conference on Advances in ICT for Emerging Regions (ICTer); 2015, p130-134, 5p