Tag
The paper proposes CB-Agent, a concept-based in-context learning method that fits a reusable concept vector from expert trajectories to score candidate actions for LLM agents, achieving top cross-benchmark averages on TextWorld, ALFWorld, and ScienceWorld.
This paper introduces the Concept-Integrated Transformer (CIT), which leverages large language models for concept supervision to achieve accurate and interpretable predictions from mobile sensing data in small-cohort health studies.
This theoretical paper studies atomic concept learning through the geometry of hypercubes and hyperplanes, showing that complexity collapses uniformly on most hyperplanes except the full diagonal, where it grows without bound. It provides a taxonomy of hyperplane behavior and a worked binary and ternary case analysis.
This paper proposes a unified geometric framework for understanding concept learning and neuron interpretation in sparse autoencoders, formalizing concepts as sets and defining detection, separation, and approximation. It provides error bounds, capacity constraints, and links to formal concept analysis, with experiments on synthetic data.
OpenAI presents a technique using energy functions to enable agents to learn and extract abstract concepts (visual, spatial, temporal, social) from tasks, then transfer these concepts to solve related tasks in different domains without retraining. The approach uses energy-based models with neural networks to perform both generation and recognition of concepts.
OpenAI presents a machine teaching approach where a teacher neural network learns to select the most illustrative examples to teach a student network to recognize concepts, producing interpretable results by grounding examples in human-understandable properties rather than arbitrary feature encodings.