SemJudge HSG Visualization for Ink-Wash Art

Paper context

Paper title: On Semiotic-Grounded Interpretive Evaluation of Generative Art Abstract: Interpretation is essential to deciphering the language of art: audiences communicate with artists by recovering meaning from visual artifacts. However, current Generative Art (GenArt) evaluators remain fixated on surface-level image quality or literal prompt adherence, failing to assess the deeper symbolic or abstract meaning intended by the creator. We address this gap by formalizing a Peircean computational semiotic theory that models Human-GenArt Interaction (HGI) as cascaded semiosis. This framework reveals that artistic meaning is conveyed through three modes - iconic, symbolic, and indexical - yet existing evaluators operate heavily within the iconic mode, remaining structurally blind to the latter two. To overcome this structural blindness, we propose SemJudge. This evaluator explicitly assesses symbolic and indexical meaning in HGI via a Hierarchical Semiosis Graph (HSG) that reconstructs the meaning-making process from prompt to generated artifact. Extensive quantitative experiments show that SemJudge aligns more closely with human judgments than prior evaluators on an interpretation-intensive fine-art benchmark. User studies further demonstrate that SemJudge produces deeper, more insightful artistic interpretations, thereby paving the way for GenArt to move beyond the generation of "pretty" images toward a medium capable of expressing complex human experience. Project page: https://github.com/songrise/SemJudge. Passages referencing this figure: ann et al. , 2022 ) , while leaving the deeper artistic meaning largely untouched. Unsurprisingly, these evaluators are often misaligned with human judgments from trained viewers (Chamberlain et al. , 2018 ; Epstein et al. , 2023 ; Samo and Highhouse, 2023 ; Kirstain et al. , 2023 ; Van Hees et al. , 2025 ; Ha et al. , 2024 ; Hullman et al. , 2023 ) . We identify two root causes of this mismatch: Figure 1. HGI as cascaded semiosis. We model HGI as a chain of meaning-making steps: a creator encodes an intention into a prompt, which the model interprets to generate an artifact. A viewer then interprets this artifact to reconstruct the meaning, which may differ from the original intention. Gap 1: Artistic meaning is not reducible to surface appearance. Instead, it is often encoded through non model then synthesizes an artifact s ( 2 ) = ρ ( 1 ) ​ ( i ( 1 ) ) s^{(2)}=\rho^{(1)}(i^{(1)}) , which is the generated art. This artifact sign is to be interpreted (i.e., evaluated) by another interpreter η ( 2 ) \eta^{(2)} , who is usually a human user. Thus, even in the simplest setting, HGI produces at least a two-round cascaded semiosis 𝒞 ( 2 ) \mathcal{C}^{(2)} , as compactly visualized in Figure 1 . Iterative generation may follow this notation to produce long cascades. 4. Semiotics-Grounded GenArt Evaluation This section first formalizes the theoretical bottleneck of the existing GenArt evaluation system. We then introduce SemJudge, a semiotic-grounded and interpretive evaluator. 4.1. Semiosis Quality Measure Under a semiotic view, evaluating the quality of HGI amounts to assessin