On measuring grounding and generalizing grounding problems

TL;DR

This paper introduces a comprehensive framework for evaluating different modes of grounding in language and symbols, emphasizing desiderata like authenticity, preservation, and robustness, and applies it to models, language, and humans.

Contribution

It recasts grounding as a multi-faceted audit rather than a binary, providing a systematic framework applicable across various grounding modes and case studies.

Findings

Model-theoretic semantics achieves exact composition but lacks etiological warrant.

Large language models show correlational fit and local robustness but lack success-driven grounding.

Humans meet grounding desiderata through evolutionary and developmental processes.

Abstract

The symbol grounding problem asks how tokens like cat can be about cats, as opposed to mere shapes manipulated in a calculus. We recast grounding from a binary judgment into an audit across desiderata, each indexed by an evaluation tuple (context, meaning type, threat model, reference distribution): authenticity (mechanisms reside inside the agent and, for strong claims, were acquired through learning or evolution); preservation (atomic meanings remain intact); faithfulness, both correlational (realized meanings match intended ones) and etiological (internal mechanisms causally contribute to success); robustness (graceful degradation under declared perturbations); compositionality (the whole is built systematically from the parts). We apply this framework to four grounding modes (symbolic; referential; vectorial; relational) and three case studies: model-theoretic semantics achieves exact composition but lacks etiological warrant; large language models show correlational fit and local robustness for linguistic tasks, yet lack selection-for-success on world tasks without grounded interaction; human language meets the desiderata under strong authenticity through evolutionary and developmental acquisition. By operationalizing a philosophical inquiry about representation, we equip philosophers of science, computer scientists, linguists, and mathematicians with a common language and technical framework for systematic investigation of grounding and meaning.