From Logic to Language: A Trust Index for Problem Solving with LLMs

TL;DR

This paper proposes a unified framework and a trust index to evaluate problem-solving in LLMs, distinguishing formal and natural language solutions and capturing their quality nuances.

Contribution

It introduces a novel trust index and statistical quality dimensions to better assess the diverse problem-solving capabilities of LLMs compared to classical methods.

Findings

The trust index Q differentiates formal correctness from natural language adequacy.

Bi-semantic entropy measures robustness and diversity in LLM answers.

Emotional valence quantifies subjective solution valuation.

Abstract

Classical computation, grounded in formal, logical systems, has been the engine of technological progress for decades, excelling at problems that can be described with unambiguous rules. This paradigm, however, leaves a vast ocean of human problems -- those characterized by ambiguity, dynamic environments, and subjective context -- largely untouched. The advent of Large Language Models (LLMs) represents a fundamental shift, enabling computational systems to engage with this previously inaccessible domain using natural language. This paper introduces a unified framework to understand and contrast these problem-solving paradigms. We define and delineate the problem spaces addressable by formal languages versus natural language. While solutions to the former problem class can be evaluated using binary quality measures, the latter requires a much more nuanced definition of approximate solution space taking into account the vagueness, subjectivity and ambiguity inherent to natural language. We therefore introduce a vector-valued trust index Q, which reflects solution quality and distinguishes the binary correctness of formal solutions from the continuous adequacy spectrum characteristic of natural language solutions. Within this framework, we propose two statistical quality dimensions. Normalized bi-semantic entropy measures robustness and conceptual diversity of LLM answers given semantic variation in problem formulations. Emotional valence maps subjective valuation of a solution to a quantifiable metric that can be maximized by invoking statistical measures. The concepts introduced in this work will provide a more rigorous understanding of the capabilities, limitations, and inherent nature of problem-solving in the age of LLMs.