Case-Based Reasoning and Large Language Model Synergies (CBR-LLM)
at Merida, Yucatán, México
Synergies Unleashed: Exploring the Fusion of Case-Based Reasoning and Large Language Models in AI
Announcing the Case-Based Reasoning and Large Language Models Synergies Workshop at ICCBR 2024 in Merida, Yucatán, México. This workshop will explore opportunities for combining Case-Based Reasoning (CBR) and Large Language Models (LLMs), fostering a deeper understanding of their synergistic potential. This workshop will present an excellent opportunity for researchers and practitioners to discuss and share their insights on this new, exciting and rapidly evolving field of AI. We look forward to your contributions and an engaging and informative workshop.
Key Dates
Submission Deadline: April 3, 2024 23:59 GMT
Notification of Acceptance: April 17, 2024
Submission Deadline for Camera-Ready Copy: May 1, 2024
Workshop Date: July 1, 2024
Accepted Papers
Florian Brand, Lukas Malburg and Ralph Bergmann. Large Language Models as Knowledge Engineers
Ian Watson. A Case-Based Persistent Memory for a Large Language Model
David Leake and Kaitlynne Wilkerson. On Implementing Case-Based Reasoning with Large Language Models*
Lasal Jayawardena, Nirmalie Wiratunga and Stewart Massie. CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering*
Mirjam Minor and Eduard Kaucher. Retrieval Augmented Generation with LLMs for Explaining Business Process Models*
* Accepted for the main conference but included for discussion in the workshop
Workshop Themes
The workshop will focus on several key areas, including but not limited to:
Integration of CBR with LLMs for enhanced reasoning and decision-making.
CBR for prompt engineering for LLMs.
CBR for Retrieval Augmented Generation (RAG) for LLMs.
CBR for explaining LLM output (XAI).
CBR to provide guardrails and improve the alignment of LLMs.
LLMs for knowledge acquisition and modelling in CBR (case extraction, vocabulary, retrieval).
Multimodal LLMs and CBR.
Applications of LLMs enhancing the capabilities of CBR systems.
Case studies showcasing successful implementations of CBR-LLM synergies.
Ethical, scalability and maintenance considerations and challenges in tusingCBR and LLMs.
Future directions and emerging trends at the intersection of CBR and LLMs.
Interest to ICCBR Attendees
2023 was the year Large Language Models broke into public attention with the release of ChatGPT. The potential of LLMs to act as a conversational interface to CBR systems for query formulation and solution explanation seems obvious but has yet to be explored. Conversely, using CBR to improve prompt engineering is another area of potential interest [Madaan et al., arXiv, 2023]. In addition, LLMs can also be used to limit the knowledge acquisition and modelling efforts for initially creating and representing knowledge in the CBR knowledge containers [Richter, 2003]. Currently, most of these approaches are used for AI planning [Liu et al., arXiv, 2023][Guan et al., arXiv, 2023], but their potential for CBR should also be investigated. Finally, the technologies associated with LLMs, such as vector databases and Approximate Nearest Neighbor retrieval [Jalali and Leake, 2018], are of great interest to CBR and due to the capabilities of large generative models, we believe many ICCBR attendees will be interested in a workshop on CBR-LLM synergies.
Cover Photo by Bhargava Marripati