Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems
This provides a larger benchmark for testing visual reasoning in AI models, though it is incremental as it builds on existing datasets.
The authors tackled the challenge of evaluating abstract visual reasoning by creating Bongard-RWR+, a dataset of 5,400 instances using real-world-like images generated via a VLM pipeline to represent fine-grained concepts from Bongard Problems, and found that state-of-the-art VLMs struggle with fine-grained concepts despite recognizing coarse-grained ones.
Bongard Problems (BPs) provide a challenging testbed for abstract visual reasoning (AVR), requiring models to identify visual concepts fromjust a few examples and describe them in natural language. Early BP benchmarks featured synthetic black-and-white drawings, which might not fully capture the complexity of real-world scenes. Subsequent BP datasets employed real-world images, albeit the represented concepts are identifiable from high-level image features, reducing the task complexity. Differently, the recently released Bongard-RWR dataset aimed at representing abstract concepts formulated in the original BPs using fine-grained real-world images. Its manual construction, however, limited the dataset size to just $60$ instances, constraining evaluation robustness. In this work, we introduce Bongard-RWR+, a BP dataset composed of $5\,400$ instances that represent original BP abstract concepts using real-world-like images generated via a vision language model (VLM) pipeline. Building on Bongard-RWR, we employ Pixtral-12B to describe manually curated images and generate new descriptions aligned with the underlying concepts, use Flux.1-dev to synthesize images from these descriptions, and manually verify that the generated images faithfully reflect the intended concepts. We evaluate state-of-the-art VLMs across diverse BP formulations, including binary and multiclass classification, as well as textual answer generation. Our findings reveal that while VLMs can recognize coarse-grained visual concepts, they consistently struggle with discerning fine-grained concepts, highlighting limitations in their reasoning capabilities.