NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings

2026-04-12

AI Summary

Standard dense retrievers inherently struggle to support multi-atomic logical constraints. This work proposes a training-free neuro-symbolic fuzzy logic framework that embeds formal t-norms and t-conorms into neural representation spaces, enabling Boolean logical operations through first-order hybrid calculus. The approach innovatively introduces Neuro-Symbolic Delta (NS-Delta) and Riemannian-optimization-driven Spherical Query Optimization (SQO) to preserve atomic semantics while preventing representational collapse, thereby supporting dynamic post-training logical reasoning. Evaluated across six encoders and two modalities, the method achieves up to an 81% relative improvement in mAP. Notably, even when applied to models already fine-tuned for logical reasoning, it yields consistent gains—averaging 20% and reaching as high as 47% in performance enhancement.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Knowledge Representation and Reasoning: Logic Programming
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Standard dense retrievers lack a native calculus for multi-atom logical constraints. We introduce Neuro-Symbolic Fuzzy Logic (NSFL), a framework that adapts formal t-norms and t-conorms to neural embedding spaces without requiring retraining. NSFL operates as a first-order hybrid calculus: it anchors logical operations on isolated zero-order similarity scores while actively steering representations using Neuro-Symbolic Deltas (NS-Delta) -- the first-order marginal differences derived from contextual fusion. This preserves pure atomic meaning while capturing domain reliance, preventing the representation collapse and manifold escape endemic to traditional geometric baselines. For scalable real-time retrieval, Spherical Query Optimization (SQO) leverages Riemannian optimization to project these fuzzy formulas into manifold-stable query vectors. Validated across six distinct encoder configurations and two modalities (including zero-shot and SOTA fine-tuned models), NSFL yields mAP improvements up to +81%. Notably, NSFL provides an additive 20% average and up to 47% boost even when applied to encoders explicitly fine-tuned for logical reasoning. By establishing a training-free, order-aware calculus for high-dimensional spaces, this framework lays the foundation for future dynamic scaling and learned manifold logic.

Problem

• dense retrieval
• logical constraints
• neural embeddings
• representation collapse
• manifold escape

Innovation

• Neuro-Symbolic Fuzzy Logic
• t-norms and t-conorms
• Neuro-Symbolic Deltas
• Spherical Query Optimization
• post-training framework