A self-distilling neuro-symbolic cascade that amortises LLM cost across knowledge-graph QA and regulatory-compliance checking, with auditable Datalog proof trees.
A verifier-anchored self-distilling neuro-symbolic cascade: a cheap, teacher-independent correctness verifier gates and corrects a frontier LLM before its answers distil into auditable, type-checked Datalog rules with proof trees.
Sample code for two-tier LLM inference (cascading) on Amazon Bedrock, using a single Bedrock Converse API surface. NVIDIA Nemotron Nano handles routine support-ticket classification on every request; Anthropic Claude Sonnet handles cases the routing logic flags as harder. Includes a bake-off harness, sample data, and tests. Next.js + TypeScript.
A leakage-controlled, paired-bootstrap-rigorous study of whether an LLM's internal TopK Sparse Autoencoder (SAE) feature spaces encode a difficulty-predictive routing signal. Benchmarked on HellaSwag (rigorous predictive null) and SQuAD continuous perplexity (positive Pareto cascade), with Platt recalibration and causal ablatings.
Add a description, image, and links to the llm-cascade topic page so that developers can more easily learn about it.
To associate your repository with the llm-cascade topic, visit your repo's landing page and select "manage topics."