Skip to main content
Search

# Neuro-Symbolic Reasoning

4 related articles

Subscribe to updates
  1. arXiv

    Intrusion detection weaves logic rules into the neural net: a few labeled packets per attack class cut false alarms from 0.075 to 0.001

    DeepWeave places interpretable logic rules and neural predictions inside one probabilistic reasoning program, so the two act as potentially conflicting evidence for each alert. Machine-learning intrusion detection previously needed large labeled attack sets, degraded under deployment shift, and offered analysts little to inspect. With only a few labeled packet observations per attack class, the Anchored DeepWeave variant raises macro-F1 by up to 34.5% over the matched neural baseline and lowers the attack false-positive rate from 0.075 to 0.001.

  2. Mental-state prediction stops guessing actions alone: separate belief and program loops lift joint accuracy to 70.8% on OpenToM

    Psychological prediction must say both what a character will do and what it believes, yet models tuned on surface patterns often return action and belief answers that disagree. A neuro-symbolic reasoning framework splits the latent cognitive state into a belief representation and an executable program representation, filters hypotheses that violate contextual constraints through energy-penalized particle resampling, and lets the two pathways update separately in stop-gradient alternating fixed-point iterations. Under the text-based classification setting on OpenToM and FANToM, the share of samples with both action and belief correct reaches 70.8% and 52.1%, above scale-matched pure encoder classifiers.

  3. arXiv

    Omni-Geo couples neural and symbolic reasoning in a unified typed geometry state, reaching 90.8% macro average across three geometry benchmarks and solving 21/30 IMO-AG-30 problems

    The work formulates dense neural–symbolic coupling, in which neural proposals and symbolic execution share one typed geometry state and communicate through executable actions at every search step, instantiated as Omni-Geo, a single solver spanning plane, analytic (including conics), and solid geometry; with Claude Sonnet 4.6 it reaches 94.2%, 88.5%, and 89.8% on FormalGeo7K, Conic10K, and SolidFGeo (90.8% macro average) and solves 21/30 IMO-AG-30 problems.

  4. arXiv

    NeuroSymb-MRG generates radiology reports via differentiable abductive reasoning and active uncertainty minimization, raising BLEU-1 to 0.602 on IU X-ray and 0.487 on MIMIC-CXR

    The work presents NeuroSymb-MRG, a framework that maps image features to probabilistic clinical concepts, composes multi-hop abductive reasoning chains through a differentiable logic layer (product t-norm AND, probabilistic sum OR, learnable gating α), decodes those chains into roughly 120 clause templates augmented with retrieved evidence and constrained LLM paraphrasing, and drives clinician-in-the-loop review with active sampling based on rule-level predictive entropy (5 MC-dropout passes) plus k-center diversity (k=16 per round); on IU X-ray and MIMIC-CXR it improves BLEU-1 through BLEU-4, ROUGE-L and METEOR over the listed representative baselines, for example IU X-ray BLEU-1 of 0.602 and MIMIC-CXR BLEU-1 of 0.487.

You’re all caught up