large language models
-
Artificial intelligence
How good are LLMs at thinking about language?
Some LLMs can now analyse sentences much like a trained linguist, challenging the notion that only humans can reflect on…
-
Artificial intelligence
Data governance practices for using RAG in generative AI-powered information systems supporting knowledge management (KM)
Research findings suggest a strong link between data governance practices and information system success across three quality dimensions.
-
Bridging the research-practice gap
Emerging sovereign systems: global examples of indigenous knowledge machine language models [Forum special series, Artificial intelligence]
KM Triversary Forum 2025 presentation article by Elizabeth (Liz) McLean.
-
Artificial intelligence
Using GraphRAG to enhance LLM-based information retrieval supporting knowledge management (KM)
Researchers evaluate the potential of artificial intelligence (AI) graph retrieval-augmented generation (GraphRAG) using the case study of the information challenges…
-
Artificial intelligence
Neurosymbolic AI is the answer to large language models’ inability to stop hallucinating
To make neurosymbolic AI fully feasible, there needs to be more research to refine their ability to discern general rules…
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Introduction to Chapter 2 – Cognition
Exploring different learning and reasoning paradigms.
-
Artificial intelligence
Responsible AI case study: integrating advanced language models with validation by domain experts
A law resources case study supports the need for 'humans in the loop' to validate AI outputs before they're used.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3.3 – Biological inspirations
Liu and colleagues' agent framework, though fundamentally computational, finds its roots in biological systems.
-
Artificial intelligence
What are small language models and how do they differ from large ones?
Small language models are like specialised tools in a toolbox, compared to something like ChatGPT that brings the whole workshop.
-
Advances & challenges in foundation agents
Advances & challenges in foundation agents: Section 1.3.2 – Core concepts and notations in the agent loop
The agent framework architecture and a formal definition of foundation agents.
