arXiv:2606. 04326v1 Announce Type: cross Abstract: Concept bottleneck models predict outcomes from high-level concepts detected in inputs.
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels.
arXiv:2512. 20638v2 Announce Type: replace-cross Abstract: The evaluation of large language models relies heavily on standardized benchmarks.
arXiv:2511. 19636v2 Announce Type: replace-cross Abstract: In many machine learning problems, there may exist multiple models that achieve nearly identical predictive performance while relying on fundamentally different internal logic.
arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
arXiv:2606. 16535v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) are a relevant tool for explainable Artificial Intelligence because they make their predictions through human-interpretable symbols.
arXiv:2602. 02886v3 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts.
arXiv:2606. 19489v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space.
arXiv:2608. 08700v1 Announce Type: new Abstract: Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents.
arXiv:2606. 11616v1 Announce Type: new Abstract: High-quality training data is essential for the success of machine learning models.
arXiv:2608. 10004v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention.
arXiv:2608. 13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.