Dr Kyle Martin's Outputs (10)

SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024) (2024)
Presentation / Conference Contribution
MARTIN, K., SALIMI, P. and WIJAYASEKARA, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the 2024 SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online]. Available from: https://ceur-ws.org/Vol-3822/

In the last few years, Large Language Models (LLMs) underpinned by rapid advancements in Artificial Intelligence (AI) have grabbed the attention of academia, industry and the general public. Demonstrating hence before unseen capability to deal with a... Read More about SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024).

Extended results for: enhancing abstract screening classification in evidence-based medicine: incorporating domain knowledge into pre-trained models. (2024)
Presentation / Conference Contribution
OFORI-BOATENG, R., ACEVES-MARTINS, M., WIRATUNGA, N. and MORENO-GARCIA, C.F. 2024. Extended results for: enhancing abstract screening classification in evidence-based medicine: incorporating domain knowledge into pre-trained models. In Martin, K., Salimi, P. and Wijayasekara, V. (eds.). Proceedings of the 2024 SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822Aachen: CEUR-WS [online], pages 11-18. Available from: https://ceur-ws.org/Vol-3822/short1.pdf

Evidence-based medicine (EBM) is a foundational element in medical research, playing a crucial role in shaping healthcare policies and clinical decision-making. However, the rigorous processes required for EBM, particularly during the abstract screen... Read More about Extended results for: enhancing abstract screening classification in evidence-based medicine: incorporating domain knowledge into pre-trained models..

Formal dialogue and large language models. (2024)
Presentation / Conference Contribution
SNAITH, M. and WELLS, S. 2024. Formal dialogue and large language models. In Martin, K., Salimi, P. and Wijayasekara, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online], pages 24-31. Available from: https://ceur-ws.org/Vol-3822/short3.pdf

In this paper, we present preliminary work into combining formal models of dialogue and large language models, before going on to discuss how this provides a foundation for similar approaches involving computational models of argument. First, we addr... Read More about Formal dialogue and large language models..

Integrating KGs and ontologies with RAG for personalised summarisation in regulatory compliance. (2024)
Presentation / Conference Contribution
ARSHAD, U., CORSAR, D. and NKISI-ORJI, I. 2024. Integrating KGs and ontologies with RAG for personalised summarisation in regulatory compliance. In Martin, K., Salimi, P. and Wijayasekara, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online], pages 56-61. Available from: https://ceur-ws.org/Vol-3822/short7.pdf

With the growing complexity and increased volumes, regulatory texts are fast becoming a significant challenge for organisations to remain compliant. Traditional ways of summarising legal texts need to be more accommodating of critical, domain-specifi... Read More about Integrating KGs and ontologies with RAG for personalised summarisation in regulatory compliance..

Towards improving open-box hallucination detection in large language models (LLMs). (2024)
Presentation / Conference Contribution
SURESH, M., ALJUNDI, R., NKISI-ORJI, I. and WIRATUNGA, N. 2024. Towards improving open-box hallucination detection in large language models (LLMs). In Martin, K., Salimi, P. and Wijayasekara, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online], pages 1-10. Available from: https://ceur-ws.org/Vol-3822/paper1.pdf

Due to the increasing availability of Large Language Models (LLMs) through both proprietary and open-sourced releases of models, the adoption of LLMs across applications has drastically increased making them commonplace in day-to-day lives. Yet, the... Read More about Towards improving open-box hallucination detection in large language models (LLMs)..

SCaLe-QA: Sri Lankan case law embeddings for legal QA. (2024)
Presentation / Conference Contribution
JAYAWARDENA, L., WIRATUNGA, N., ABEYRATNE, R., MARTIN, K., NKISI-ORJI, I. and WEERASINGHE, R. 2024. SCaLe-QU: Sri Lankan case law embeddings for legal QA. In Martin, K., Salimi, P. and Wijayasekara, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online], pages 47-55. Available from: https://ceur-ws.org/Vol-3822/short6.pdf

SCaLe-QA is a foundational system developed for Sri Lankan Legal Question Answering (LQA) by leveraging domain-specific embeddings derived from Supreme Court cases. The system is tailored to capture the unique linguistic and structural characteristic... Read More about SCaLe-QA: Sri Lankan case law embeddings for legal QA..

Dual-task dialogue understanding. (2024)
Presentation / Conference Contribution
ANWAR, S., WIRATUNGA, N. and SNAITH, M. 2024. Dual-task dialogue understanding. In Martin, K., Salimi, P. and Wijayasekara, V. (eds.) 2024. SICSA REALLM workshop 2024: proceedings of the SICSA (Scottish Informatics and Computer Science Alliance) REALLM (Reasoning, explanation and applications of large language models) workshop (SICSA REALLM workshop 2024), 17 October 2024, Aberdeen, UK. CEUR workshop proceedings, 3822. Aachen: CEUR-WS [online], pages 40-46. Available from: https://ceur-ws.org/Vol-3822/short5.pdf

In dialogue systems, utterances do not occur in isolation. One conversation might involve interactions between several speakers. It's crucial to determine the intentions behind utterances in multi-party conversations when more than two interlocutors... Read More about Dual-task dialogue understanding..

Building personalised XAI experiences through iSee: a case-based reasoning-driven platform. (2024)
Presentation / Conference Contribution
CARO-MARTÍNEZ, M., LIRET, A., DÍAZ-AGUDO, B., RECIO-GARCÍA, J.A., DARIAS, J., WIRATUNGA, N., WIJEKOON, A., MARTIN, K., NKISI-ORJI, I., CORSAR, D., PALIHAWADANA, C., PIRIE, C., BRIDGE, D., PRADEEP, P. and FLEISCH, B. 2024. Building personalised XAI experiences through iSee: a case-based reasoning-driven platform. In Longo, L., Liu, W. and Montavon, G. (eds.) xAI-2024: LB/D/DC: joint proceedings of the xAI 2024 late-breaking work, demos and doctoral consortium, co-located with the 2nd World conference on eXplainable artificial intelligence (xAI 2024), 17-19 July 2024, Valletta, Malta. Aachen: CEUR-WS [online], 3793, pages 313-320. Available from: https://ceur-ws.org/Vol-3793/paper_40.pdf

Nowadays, eXplainable Artificial Intelligence (XAI) is well-known as an important field in Computer Science due to the necessity of understanding the increasing complexity of Artificial Intelligence (AI) systems or algorithms. This is the reason why... Read More about Building personalised XAI experiences through iSee: a case-based reasoning-driven platform..

iSee: a case-based reasoning platform for the design of explanation experiences. (2024)
Journal Article
CARO-MARTÍNEZ, M., RECIO-GARCÍA, J.A., DÍAZ-AGUDO, B., DARIAS, J.M., WIRATUNGA, N., MARTIN, K., WIJEKOON, A., NKISI-ORJI, I., CORSAR, D., PRADEEP, P., BRIDGE, D. and LIRET, A. 2024. iSee: a case-based reasoning platform for the design of explanation experiences. Knowledge-based systems [online], 302, article number 112305. Available from: https://doi.org/10.1016/j.knosys.2024.112305

Explainable Artificial Intelligence (XAI) is an emerging field within Artificial Intelligence (AI) that has provided many methods that enable humans to understand and interpret the outcomes of AI systems. However, deciding on the best explanation app... Read More about iSee: a case-based reasoning platform for the design of explanation experiences..

CBR-RAG: case-based reasoning for retrieval augmented generation in LLMs for legal question answering. (2024)
Presentation / Conference Contribution
WIRATUNGA, N., ABEYRATNE, R., JAYAWARDENA, L., MARTIN, K., MASSIE, S., NKISI-ORJI, I., WEERASINGHE, R., LIRET, A. and FLEISCH, B. 2024. CBR-RAG: case-based reasoning for retrieval augmented generation in LLMs for legal question answering. In Recio-Garcia, J.A., Orozco-del-Castillo, M.G. and Bridge, D (eds.) Case-based reasoning research and development: proceedings of the 32nd International conference of case-based reasoning research and development 2024 (ICCBR 2024), 1-4 July 2024, Merida, Mexico. Lecture notes in computer science, 14775. Cham: Springer [online], pages 445-460. Available from: https://doi.org/10.1007/978-3-031-63646-2_29

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... Read More about CBR-RAG: case-based reasoning for retrieval augmented generation in LLMs for legal question answering..