From the 1 of 5 linked papers with an AI index.
5 papers
How Much Do Legal RAG Systems Still Hallucinate?
Souvick Das, Sallam Abualhaija, Domenico Bianculli
Hallucination is a major challenge for retrieval-augmented generation (RAG) systems in the legal domain, where ungrounded answers can lead to serious consequences. To better unders…
GDPR-Relevant Privacy Concerns in Mobile Apps Research: A Systematic Literature Review
Orlando Amaral Cejas, Nicolas Sannier, Sallam Abualhaija +2
The paper systematically reviews 60 studies on GDPR-related privacy concerns in mobile applications, identifying main focus areas such as direct data collection, data sharing with…
LLM-Driven Cost-Effective Requirements Change Impact Analysis
Romina Etezadi, Sallam Abualhaija, Chetan Arora +1
Requirements are inherently subject to change throughout the software development lifecycle. Within the limited budget available to requirements engineers, manually identifying the…
Fine-grained Claim-level RAG Benchmark for Law
Souvick Das, Sallam Abualhaija, Domenico Bianculli
The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-…
Classifier or Prompt: A Case Study on Legal Requirements Traceability
Romina Etezadi, Sallam Abualhaija, Chetan Arora +1
New regulations are introduced to ensure software development aligns with ethical concerns and protects public safety. Showing compliance requires tracing requirements to legal pro…