Computational Hermeneutics: Evaluating generative AI as a cultural technology

TL;DR

This paper proposes a hermeneutic framework for evaluating generative AI as cultural technologies, emphasizing context, plurality, and ambiguity in interpretive processes.

Contribution

It introduces computational hermeneutics as a new interpretive approach and offers principles for culturally aware AI evaluation.

Findings

Benchmarks should be iterative and context-aware.

Evaluation should include human perspectives, not just models.

Focus on cultural context rather than only output accuracy.

Abstract

Generative AI systems are increasingly recognized as cultural technologies, yet current evaluation frameworks often treat culture as a variable to be measured rather than fundamental to the system's operation. Drawing on hermeneutic theory from the humanities, we argue that GenAI systems function as "context machines" that must inherently address three interpretive challenges: situatedness (meaning only emerges in context), plurality (multiple valid interpretations coexist), and ambiguity (interpretations naturally conflict). We present computational hermeneutics as an emerging framework offering an interpretive account of what GenAI systems do, and how they might do it better. We offer three principles for hermeneutic evaluation -- that benchmarks should be iterative, not one-off; include people, not just machines; and measure cultural context, not just model output. This perspective offers a nascent paradigm for designing and evaluating contemporary AI systems: shifting from standardized questions about accuracy to contextual ones about meaning.