Rumbidzai Chitakunye

Rumbidzai Chitakunye

Auto-generated profile, based on publicly available information

Rumbidzai Chitakunye

Vrije Universiteit Amsterdam, Amsterdam, Netherlands

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 November 2023
Verified
Conference Paper
Open access
RCRumbidzai Chitakunye
Rumbidzai Chitakunye
HWHeike Winschiers-Theophilus
Heike Winschiers-Theophilus
Vera De CauwerVera De Cauwer
Vera De Cauwer
SMSebastian Mukumbira
Sebastian Mukumbira
Passing on of ethnobotanical knowledge orally is becoming a less common practice, thus resulting in knowledge loss for the future generation. Hence, it is crucial to digitally preserve ethnobotanical knowledge. A number of national ethnobotanical databases have been developed across the globe. However, They are mainly used for commercialisation or research purposes without providing access to the original knowledge holders. Moreover the indigenous communities mostly served as informants only not validating the digitalizations. This results in incompleteness, misinterpretations and inaccuracy of the digital data sets. Hence, the main objective of this project was to develop a digital tool with indigenous communities living in Kunene to support the safeguarding of traditional plant knowledge. Following a community-based co-design approach and an iterative prototyping development a mobile ethnographic app was implemented, enabling indigenous communities to collect and curate their own data, which they can then share with external entities.

12 April 2026
Verified
Conference Paper
Open access
PKPelin Rabia Kuran
Pelin Rabia Kuran
RCRumbidzai Chitakunye
Rumbidzai Chitakunye
VSVincenzo Stoico
Vincenzo Stoico
IHIlja Heitlager
Ilja Heitlager
JBJustus Bogner
Justus Bogner
The rapid adoption of large language models (LLMs) has raised concerns about their substantial energy consumption, especially when deployed at industry scale. While several techniques have been proposed to address this, limited empirical evidence exists regarding the effectiveness of applying them to LLM-based industry applications. To fill this gap, we analyzed a chatbot application in an industrial context at Schuberg Philis, a Dutch IT services company. We then selected four techniques, namely Small and Large Model Collaboration, Prompt Optimization, Quantization, and Batching, applied them to the application in eight variations, and then conducted experiments to study their impact on energy consumption, accuracy, and response time compared to the unoptimized baseline. Our results show that several techniques, such as Prompt Optimization and 2-bit Quantization, managed to reduce energy use significantly, sometimes by up to 90%. However, these techniques especially impacted accuracy negatively, to a degree that is not acceptable in practice. The only technique that achieved significant and strong energy reductions without harming the other qualities substantially was Small and Large Model Collaboration via Nvidia’s Prompt Task and Complexity Classifier (NPCC) with prompt complexity thresholds. This highlights that reducing the energy consumption of LLM-based applications is not difficult in practice. However, improving their energy efficiency, i.e., reducing energy use without harming other qualities, remains challenging. Our study provides practical insights to move towards this goal.