Building A Unified AI-centric Language System: analysis, framework and future work
Edward Hong Wang, Cynthia Xin Wen
TL;DR
Addresses inefficiencies and biases arising from using natural languages for extended AI reasoning. Proposes an AI-centric, unambiguous language to improve token efficiency and reduce bias, informed by Transformer structure, emergent AI communication, and constructed languages. Outlines a concrete implementation framework (pre-processing translation, training on the AI-friendly language, and back-translation at inference) and discusses potential gains in memory and compute with possible model simplification. Describes a path to empirical validation via toy-language experiments and envisions a universal interchange format for AI-to-AI and human-to-AI interactions with broader impact on fairness and performance.
Abstract
Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found in natural languages. This paper explores the design of a unified AI-centric language system that addresses these challenges by offering a more concise, unambiguous, and computationally efficient alternative to traditional human languages. We analyze the limitations of natural language such as gender bias, morphological irregularities, and contextual ambiguities and examine how these issues are exacerbated within current Transformer architectures, where redundant attention heads and token inefficiencies prevail. Drawing on insights from emergent artificial communication systems and constructed languages like Esperanto and Lojban, we propose a framework that translates diverse natural language inputs into a streamlined AI-friendly language, enabling more efficient model training and inference while reducing memory footprints. Finally, we outline a pathway for empirical validation through controlled experiments, paving the way for a universal interchange format that could revolutionize AI-to-AI and human-to-AI interactions by enhancing clarity, fairness, and overall performance.