The paper surveys computational models that use programs as representations for concepts, arguing that programs could serve as a universal language for concepts. It highlights how humans learn and generalize from sparse data by expressing knowledge in rich structural formats, and evaluates how program-based models contribute to this goal. The authors propose that adopting programs as a universal representational language could enhance concept learning across diverse domains.
arXiv:2606. 07007v1 Announce Type: cross Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs).
The paper reviews Cobweb, a computational model of categorization and concept formation, and extends it to include chunks and their acquisition. It introduces rellis/, an implementation that applies this unified theory to learning context-free grammars, demonstrating the system’s ability to represent syntactic knowledge, parse and generate sentences, and learn compositional structures from sample parses. The authors discuss related work on concepts and chunks and suggest directions for future research.
arXiv:2512. 07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge.
The paper introduces Mapping the Concept Landscape (MCL), a framework that replaces high‑dimensional feature embeddings with explicit sample‑level graphs of entities, events, and attributes for image‑caption pairs. By aggregating these graphs into a dataset‑level graph, MCL captures the global distribution of semantic concepts and identifies rare concepts. A greedy algorithm then selects samples to maximize coverage of under‑represented concepts, achieving better pruning efficiency and providing a transparent audit trail.
arXiv:2603. 01227v3 Announce Type: replace Abstract: We propose the Lattice Representation Hypothesis of large language models: a symbolic backbone that grounds conceptual hierarchies and logical operations in embedding geometry.
arXiv:2607. 04548v1 Announce Type: cross Abstract: Novel category discovery aims to identify unseen classes from unlabeled data by transferring knowledge from labeled categories, but most existing methods perform discovery in opaque latent feature spaces.
arXiv:2606. 09653v1 Announce Type: new Abstract: Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions.
The paper examines convergence problems in Relational Concept Analysis (RCA) when applied to AOC-posets instead of full concept lattices. It explains why RCA’s iterative process may fail to converge in the AOC-poset setting, identifies conditions that can still guarantee convergence, and proposes a convergent variant that preserves the AOC-poset structure by never removing relational attributes. The study also discusses data transformations that can restore convergence.
arXiv:2602. 02886v3 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts.
arXiv:2606. 16193v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret.
arXiv:2609.24554v1 Announce Type: new Abstract: Concepts are commonly defined as abstract, compact representations of knowledge and treated as basic units of intelligent behavior. Yet, cognition, psy...
arXiv:2509. 22015v2 Announce Type: replace Abstract: Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, providing a powerful lens for passive feature discovery.