Legal Question Answering
Legal Question Answering (LQA) focuses on developing AI systems capable of accurately and efficiently answering legal questions using natural language processing. Current research emphasizes improving the accuracy and interpretability of LQA systems by integrating large language models (LLMs) with retrieval-augmented generation (RAG) techniques, often incorporating case-based reasoning and leveraging domain-specific knowledge to enhance performance. This field is significant for improving access to legal information and potentially automating aspects of legal research and analysis, particularly in areas with limited legal resources or expertise.
Papers
CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering
Nirmalie Wiratunga, Ramitha Abeyratne, Lasal Jayawardena, Kyle Martin, Stewart Massie, Ikechukwu Nkisi-Orji, Ruvan Weerasinghe, Anne Liret, Bruno Fleisch
NLP at UC Santa Cruz at SemEval-2024 Task 5: Legal Answer Validation using Few-Shot Multi-Choice QA
Anish Pahilajani, Samyak Rajesh Jain, Devasha Trivedi