Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding

TL;DR

This paper argues that shaping schemas through advanced language representation is crucial for expanding LLM intelligence, supported by formalization and empirical evidence showing performance improvements through language design.

Contribution

It formalizes the importance of language representation in LLMs and provides empirical evidence that deliberate language design enhances performance without changing model scale.

Findings

Performance gains from deliberate language representation design

LLM internal features vary with different language representations

Controlled experiments show language structure impacts task understanding

Abstract

Although natural language is the default medium for Large Language Models (LLMs), its limited expressive capacity creates a profound bottleneck for complex problem-solving. While recent advancements in AI have relied heavily on scaling, merely internalizing knowledge does not guarantee its effective application. Defining language representation as the linguistic and symbolic constructs used to map and model the real world, this paper argues that shaping schemas through advanced language representation is the next frontier for expanding LLM intelligence. We posit that an LLM's knowledge activation and organization -- its schema -- depends heavily on the structural and symbolic sophistication of the language used to represent a given task. This paper contributes both a formalization of this claim and the empirical evidence to support it. With a new formalization, we present multiple lines of evidence to support our position: Firstly, we review recent empirical practices and emerging methodologies that demonstrate the substantial performance gains achievable through deliberate language representation design, even without modifying model parameters or scale. Secondly, we conduct controlled experiments showing that LLM performance and its internal feature activations vary under different language representations of the same underlying task. Together, these findings highlight language representation design as a promising direction for future research.