Assessing LLMs in Art Contexts: Critique Generation and Theory of Mind Evaluation
This work addresses the problem of evaluating LLMs' interpretative and reasoning abilities in art for AI researchers and cognitive scientists, but it is incremental as it builds on existing methods for critique generation and ToM evaluation.
This study assessed large language models (LLMs) in art contexts by generating critiques of artworks and evaluating Theory of Mind (ToM) in art-related situations, finding that AI-generated critiques were often indistinguishable from human ones in Turing tests and that LLM performance on ToM tasks varied, revealing cognitive limitations and potential.
This study explored how large language models (LLMs) perform in two areas related to art: writing critiques of artworks and reasoning about mental states (Theory of Mind, or ToM) in art-related situations. For the critique generation part, we built a system that combines Noel Carroll's evaluative framework with a broad selection of art criticism theories. The model was prompted to first write a full-length critique and then shorter, more coherent versions using a step-by-step prompting process. These AI-generated critiques were then compared with those written by human experts in a Turing test-style evaluation. In many cases, human subjects had difficulty telling which was which, and the results suggest that LLMs can produce critiques that are not only plausible in style but also rich in interpretation, as long as they are carefully guided. In the second part, we introduced new simple ToM tasks based on situations involving interpretation, emotion, and moral tension, which can appear in the context of art. These go beyond standard false-belief tests and allow for more complex, socially embedded forms of reasoning. We tested 41 recent LLMs and found that their performance varied across tasks and models. In particular, tasks that involved affective or ambiguous situations tended to reveal clearer differences. Taken together, these results help clarify how LLMs respond to complex interpretative challenges, revealing both their cognitive limitations and potential. While our findings do not directly contradict the so-called Generative AI Paradox--the idea that LLMs can produce expert-like output without genuine understanding--they suggest that, depending on how LLMs are instructed, such as through carefully designed prompts, these models may begin to show behaviors that resemble understanding more closely than we might assume.