Tag
A survey paper analyzing over 50 neurosymbolic AI systems, comparing Datalog, answer set programming, and probabilistic logic programs across semantics, expressiveness, neural integration, and evaluation, with a decision matrix and open-problem roadmap for choosing rule-based languages.
Stanford's Monica Lam team has released CS224V "Agentic AI," a research course focused on anti-hallucination and accountability. Using retrieval, declarative specifications, theorem provers, and rigorous evaluation, it turns unreliable LLMs into trustworthy agents, with projects accounting for 65% of the grade.
This paper presents a neurosymbolic router that uses grammatical inference (L* algorithm) to learn a DFA-based dispatcher, sending structured queries to deterministic symbolic solvers and reserving small language models for open-ended problems on edge hardware. Evaluated on a Raspberry Pi 4B, the router achieves 98.3% overall accuracy and runs 8.8x faster than Program-of-Thought baselines.
Crucible is an experimental neurosymbolic stack integrating Mamba2 with Z3 verification, JEPA for concept prediction, and HDC memory, designed for free Kaggle T4 sessions.
The paper introduces a neurosymbolic framework that uses LLMs as adaptive proposal distributions to generate causal hypotheses for modeling adverse pregnancy outcomes, combining prior knowledge with empirical data scoring to improve causal discovery.
This paper introduces the RAIL principles (Reasoning, Assurances, Interfacing, Learning) for designing neurosymbolic AI systems that integrate machine learning with symbolic reasoning, arguing this approach is crucial for reliable, efficient, and trustworthy AI.
This paper presents a homotopy-type-theoretic generalization of neurosymbolic inference that preserves symmetry information and proof multiplicity, showing that this framework recovers classical inference when symmetries are trivial and yields shortcut-aware concept posteriors computable in closed form, with practical improvements on reasoning-shortcut benchmarks.
This position paper proposes the TRISM framework that integrates NeuroSymbolic AI with LLMs and RAG to address hallucination and interpretability issues in legal AI, introducing RASOR RAG for generating interpretable rationales and formalizing symbolic legal knowledge bases.
This paper accelerates the NeurASP neurosymbolic AI framework by implementing vectorization, batch processing, and caching, achieving multiple orders of magnitude speedup on larger tasks.
This paper presents a systematic human audit of NL-to-FOL datasets FOLIO and MALLS, finding 39% and 36% incorrect formalizations respectively. It releases corrected ground truths and an LLM-assisted framework to focus human relabeling, reducing the review workload to under 24% of instances for 90% accuracy.
This paper provides an algebraic formalization of the Theory of Dyadic Morality using structural causal modeling, and demonstrates applications to AI policy design.
This paper introduces LANTERN, a framework for multi-source neurosymbolic transfer in reinforcement learning that uses LLMs to generate task automata and adaptive gating to improve sample efficiency.