Search results

Facing the Music – challenges and changes

This field report examines initiatives in music lifelong learning through the research network Lifelong Learning in Music (LLM) of the Prince Claus Conservatoire in the Netherlands. LLM collaborates with other schools on various projects. As well, there is an innovative masters programme ‘New audiences and innovative practices’ with a variety of partners.

Interactieve kennisrepresentaties

Unveiling gender bias in LLM-generated hero and heroine narratives.

Meaningful music in health care

A musical improvisation inspired by a beautifulsummer day or by a song by Elvis; for patientsadmitted in hospital for an operation, music canhave healing powers. With the research projectMeaningful Music in Health Care (MiMiC), thattook place from autumn 2015 until 2018, the researchgroup Lifelong Learning in Music (LLM), togetherwith the department of surgery of the UniversityMedical Center Groningen (UMCG), researched thepractice of live music for hospital patients and theirhealth care professionals. For the research groupLifelong Learning in Music the focus of the researchwas on the meaning of this musical practice formusicians and health care professionals, and onthe development of this practice.The research of UMCG concentrated on the effectsof live music on the recovery and wellbeing of patients

Interdisciplinary Research Project ‘AI Shield’

In the modern day and age, cybersecurity facesnumerous challenges. Computer systems and networks become more and more sophisticated and interconnected, and the attack surface constantly increases. In addition, cyber-attacks keep growing in complexity and scale. In order to address these challenges, security professionals started to employ generative AI (GenAI) to quickly respond to attacks. However, this introduces challenges in terms of how GenAI can be adapted to the security environment and where the legal and ethical responsibilities lie. The Universities of Twente and Groningen and the Hanze University of Applied Sciences have initiated an interdisciplinary research project to investigate the legal and technical aspects of these LLMs in the cybersecurity domain and develop an advanced AI-powered tool.

The Impact of Quantization on Retrieval-Augmented Generation: An Analysis of Small LLMs

Post-training quantization reduces the computational demand of Large Language Models (LLMs) but can weaken some of their capabilities. Since LLM abilities emerge with scale, smaller LLMs are more sensitive to quantization. In this paper, we explore how quantization affects smaller LLMs’ ability to perform retrieval-augmented generation (RAG), specifically in longer contexts. We chose personalization for evaluation because it is a challenging domain to perform using RAG as it requires long-context reasoning over multiple documents. We compare the original FP16 and the quantized INT4 performance of multiple 7B and 8B LLMs on two tasks while progressively increasing the number of retrieved documents to test how quantized models fare against longer contexts. To better understand the effect of retrieval, we evaluate three retrieval models in our experiments. Our findings reveal that if a 7B LLM performs the task well, quantization does not impair its performance and long-context reasoning capabilities. We conclude that it is possible to utilize RAG with quantized smaller LLMs.