Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models
cs.LG, cs.AI
Submitted: 2026-05-18
Updated: 2026-09-28
License: http://creativecommons.org/licenses/by/4.0/
The gist: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applications.
Terminology
Abstract
Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enhanced reliability in high-stakes applications. They work by first extracting high-level concepts from the input and then inferring a task label from these compatibly with given logical constraints. Yet, their label and concept predictions can be overconfident, making it difficult for stakeholders to gauge when the model's decisions can be trusted. We address this issue by integrating ideas from Conformal Prediction (CP), a framework providing rigorous, distribution-free coverage guarantees. We formalize three desiderata -- consistency, coverage, and conciseness -- that any conformal method for NeSy-CBMs should satisfy, and show that existing approaches fall short of at least one. We then introduce COCOCO, a post-hoc framework that conformalizes concepts and labels jointly and reconciles them via a single deduction-abduction revision step. COCOCO satisfies all three desiderata, retains distribution-free coverage, is robust to imperfect knowledge and supports user-specified size budgets. Our experiments on 8 data sets highlight how COCOCO compares favorably against competitors and natural baselines in terms of performance and set size.
Sources
- Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts
- E-Values Expand the Scope of Conformal Prediction
- Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens
- Towards Human-AI Complementarity in Matching Tasks
- The Theory and Practice of MAP Inference over Non-Convex Constraints
- Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Prediction
- Are Training Resources Insufficient? Predict First Then Explain!
- A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference
- Neurosymbolic Conformal Classification
- Quasar: A Programming Language Specialized for LLM Code Actions
- Abductive Knowledge Induction From Raw Data
- Constraint-Aware Neurosymbolic Uncertainty Quantification with Bayesian Deep Learning for Scientific Discovery
- To Ask or Not to Ask: Learning to Require Human Feedback
- Measuring Evidence against Exchangeability and Group Invariance with E-values
- Enhancing Conformal Prediction Using E-Test Statistics
- LTNtorch: PyTorch Implementation of Logic Tensor Networks
- Adam: A Method for Stochastic Optimization
- Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks