Computational Hermeneutics: Evaluating generative AI as a cultural technology
For AI researchers and evaluators, this paper offers a conceptual shift from accuracy-based to meaning-based evaluation, but remains a theoretical perspective without empirical validation.
The paper argues that generative AI systems are cultural technologies requiring evaluation frameworks that address interpretive challenges (situatedness, plurality, ambiguity), and proposes computational hermeneutics with three principles for evaluation. No concrete results or numbers are provided.
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.