LLM world models pass mechanical checks but miss intended structure
Of 134 valid game-track models, mean structural F1 is 0.366 and only 28 exactly match the reference.
Stories per day · 30 days
2 RSS
Relatedintrusion-detection2benchmark1design-patterns1explainable-ai1gemma1hybrid-ai1interpretability1language-models1llama1logic-puzzles1ml-based-nids1multi-step-attacks1network-detection1neural-networks1planning1reasoning1rule-engines1sparse-autoencoders1
9 stories, newest first · one card per story
Stories tagged #neuro-symbolic
DeepChronos detects multi-step attacks with phase rules
On DARPA 2000 and AIT-LDS V2, authors report up to 11.3% higher macro F1 and no causal violations.
Neuro-symbolic framework solves Zebra puzzles from natural language
Combines LLM semantic parsing with symbolic exact cover solver for reliable logic puzzle solving.
DeepWeave neuro-symbolic NIDS improves low-data detection and provides explanations
DeepWeave combines neural predictions with interpretable rules for robust, label-efficient NIDS.
Paper catalogues 13 patterns for coupling language models with rules
It adds five invariants, five failure patterns, and a decision guide based on the authors’ measurements.
SAE-IDF matches symbols across systems using sparse autoencoder codes
On 12 tasks across six symbolic systems, SAE-IDF beats the same LLM's dense baseline by up to 45 points.
NeuSOGA3D: A Neuro-Symbolic Framework for Explainable 3D Geometric Reconstruction
NeuSOGA3D combines learned perception with symbolic spline reasoning to produce explainable, CAD-compatible 3D reconstructions from point clouds across all forty ModelNet40 categories.
Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting
Semi-automated pipeline converts Trivy, Semgrep, Nmap output into MulVAL attack graphs for agentic pentesting, 53.7% mean vulnerability coverage in CyBench.
Askeal, the AI cybersecurity assistant that gives verifiable, expert-backed answers
AI security startup Askeal launches with $1.1 million pre-seed, pairing generative AI with 270+ vetted cybersecurity experts for verifiable answers.
3