Large language models (LLMs) exhibit decision-making patterns that can diverge significantly from human cognition, raising concerns about their validity as proxies for human subjects in research. This paper presents a novel Shapley value-based approach to quantify the relative contribution of each prompt component in shaping LLM outputs, revealing the outsized impact of "token noise" - tokens with minimal informative content - on LLM decisions. The findings underscore the need for a more nuanced understanding of LLM behavior and caution against over-relying on these models as substitutes for human subjects.
This review provides an in-depth analysis of the current state of multi-modal large language models (MM-LLMs), covering their historical development, technical advancements, applications, and ethical considerations. It examines the role of attention mechanisms, the benefits and drawbacks of proprietary versus open-source models, and the latest innovations in MM-LLMs such as BLIP-2, LLaVA, Kosmos-1, MiniGPT4, and mPLUG-OWL.
Achieving energy efficiency in large language model (LLM) inference serving without compromising performance is crucial for sustainable and cost-effective deployment of these models in data centers.