REVIEW 8 cited by
Concept Bottleneck Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We seek to learn models that we can interact with using high-level concepts: if the model did not think there was a bone spur in the x-ray, would it still predict severe arthritis? State-of-the-art models today do not typically support the manipulation of concepts like "the existence of bone spurs", as they are trained end-to-end to go directly from raw input (e.g., pixels) to output (e.g., arthritis severity). We revisit the classic idea of first predicting concepts that are provided at training time, and then using these concepts to predict the label. By construction, we can intervene on these concept bottleneck models by editing their predicted concept values and propagating these changes to the final prediction. On x-ray grading and bird identification, concept bottleneck models achieve competitive accuracy with standard end-to-end models, while enabling interpretation in terms of high-level clinical concepts ("bone spurs") or bird attributes ("wing color"). These models also allow for richer human-model interaction: accuracy improves significantly if we can correct model mistakes on concepts at test time.
Forward citations
Cited by 8 Pith papers
-
CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models
A sparse dictionary learned from an ECG foundation model's embeddings recovers interpretable cardiac concepts—PVCs, atrial fibrillation, bundle branch blocks, ST/T-wave segments—and transfers to an external dataset wi...
-
Interpretable Failure Detection with Human-Level Concepts
ORCA ranks concept activations from CLIP and uses the rank-weighted agreement of the top-K concepts with the predicted category as its confidence score, improving failure-detection FPR on several benchmarks.
-
Concept-based Visual Counterfactual Explanations with Diffusion Models
C-VCE embeds a concept-bottleneck classifier inside a diffusion generator so counterfactual edits are steered by interpretable attributes and a gradient mask, beating L-DVCE on proximity and realism but not on flip ra...
-
Human-AI Co-design for Clinical Prediction Models
HACHI, an iterative human-AI loop that turns clinical notes into small interpretable yes/no-concept risk scores, outperforms standard instruments in two retrospective UCSF case studies.
-
Evaluating SAE interpretability without explanations
SAE latent interpretability can be scored directly from activation examples via intruder detection and embedding clustering, with LLM scores correlating strongly with human scores.
-
Wanting to Be Understood Explains the Meta-Problem of Consciousness
A social motivation to be understood, combined with the severe bandwidth limit of language, explains why conscious experience feels ineffable and why the hard problem of consciousness persists.
-
Beyond Explainable AI (XAI): An Overdue Paradigm Shift and Post-XAI Research Directions
Current XAI methods for DNNs and LLMs rest on paradoxes and false assumptions that demand a paradigm shift to verification protocols, scientific foundations, context-aware design, and faithful model analysis rather th...
-
Platonic Projection Structures: Operator-Induced Observability in Representation Learning
The paper introduces 'Platonic Projection Structures,' a reformulation of standard PSD operator theory applied to representation learning, with experiments that verify definitions rather than test predictions.
Discussion (0). Continue with ORCID to comment.