Efficient Strategy for Improving Large Language Model (LLM) Capabilities
This work addresses the computational efficiency problem for deploying LLMs, but it appears incremental as it builds on existing methods without introducing a new paradigm.
The paper tackled the problem of high computational resource requirements for deploying large language models by proposing a strategy combining data processing, selection, training, and architectural adjustments to improve efficiency in resource-constrained environments. The result included systematic evaluations of variants in terms of capability, versatility, response time, and safety, with comparative tests validating the effectiveness of the strategies.
Large Language Models (LLMs) have become a milestone in the field of artificial intelligence and natural language processing. However, their large-scale deployment remains constrained by the need for significant computational resources. This work proposes starting from a base model to explore and combine data processing and careful data selection techniques, training strategies, and architectural adjustments to improve the efficiency of LLMs in resource-constrained environments and within a delimited knowledge base. The methodological approach included defining criteria for building reliable datasets, conducting controlled experiments with different configurations, and systematically evaluating the resulting variants in terms of capability, versatility, response time, and safety. Finally, comparative tests were conducted to measure the performance of the developed variants and to validate the effectiveness of the proposed strategies. This work is based on the master's thesis in Systems and Computer Engineering titled "Efficient Strategy for Improving the Capabilities of Large Language Models (LLMs)".