SICSA-REALLM 2024
SICSA REALLM Workshop 2024

Table of Contents

• Preface
  Summary: There were 10 papers submitted for peer-review to this workshop. Out of these, 8 papers were accepted for presentation during the workshop.

Session 1: LLMs and Applications

• Towards Improving Open-box Hallucination Detection in Large Language Models (LLMs) 1 - 10
  Malavika Suresh, Rahaf Aljundi, Ikechukwu Nkisi-Orji, Nirmalie Wiratunga
• Extended Results for Enhancing Abstract Screening Classification in Evidence-Based Medicine: Incorporating Domain Knowledge into Pre-trained Models 11-18
  Regina Ofori-Boateng, Magaly Aceves-Martins, Nirmalie Wiratunga, Carlos Francisco Moreno-Garcia
• Towards LLM-driven Automated Verification of Best Practices in Digital Public Infrastructures 19 - 23
  Milan Markovic, Somayajulu Sripada, Sujit Kumar Chakrabarti, Raghuram Diddigi

Session 2: Reasoning with Natural Language

• Formal Dialogue and Large Language Models 24 - 31
  Mark Snaith, Simon Wells
• Evaluating Large Language Models on Qualitative Reasoning Tasks: A Case Study using OpenAI GPT Models 32 - 39
  Najwa AlGhamdi, Kwabena Nuamah, Alan Bundy
• Dual-Task Dialogue Understanding 40 - 46
  Sibgha Anwar, Nirmalie Wiratunga, Mark Snaith

Session 3: Retrieval-Augmented Generation

• SCaLe-QA: Sri lankan Case Law Embeddings for Legal QA 47 - 55
  Lasal Jayawardena, Nirmalie Wiratunga, Ramitha Abeyratne, Kyle Martin, Ikechukwu Nkisi-Orji, Ruvan Weerasinghe
• Integrating KGs and Ontologies with RAG for Personalised Summarisation in Regulatory Compliance 56 - 61
  Umair Arshad, David Corsar, Ikechukwu Nkisi-Orji