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

TL;DR

NSFL introduces a training-free neuro-symbolic fuzzy logic framework for neural embeddings, enhancing multi-atom logical reasoning and retrieval performance without retraining.

Contribution

It adapts formal t-norms and t-conorms to neural spaces, using Neuro-Symbolic Deltas for active representation steering, preventing collapse and manifold escape.

Findings

Achieves up to +81% mAP improvement across six encoder configurations.

Provides a 20% average and up to 47% boost even with fine-tuned encoders.

Enables scalable real-time retrieval with Riemannian optimization.

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.