paper
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
paperactiveprovisional
which-models-are-our-models-built-on-auditing-invisible-dependencies-in-modern-llms-8851393e·1 events·first seen 6d agoAliases: Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
Co-occurring entities
More like this (12)
Operadic consistency: a label-free signal for compositional reasoning failures in LLMsContinual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMsBackdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMsOperads for compositional reasoning in LLMscode synthesis LLMsA sleep-like consolidation mechanism for LLMsSIMMER: Benchmarking Latent Failures in LLM Executable Planning with a World ModelFlaws in the LLM Automation NarrativeScaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight VerifierLatent Context Language ModelsLanguage Model Safety MonitorLearning from the Self-future: On-policy Self-distillation for dLLMs
Recent events (1)
ModSleuth: Agentic system audits invisible dependency graphs in modern LLM training pipelines
Researchers introduce ModSleuth, an agentic system that recursively reconstructs LLM dependency graphs from public artifacts, recovering 1,060 source-verified dependencies across four major LLM releases. The system formalizes direct and indirect dependencies and operation-centered relationships to handle fragmented, inconsistent documentation. Applied at scale, the resulting graphs expose multi-hop license obligations, train-evaluation coupling, and discrepancies between released and training-time artifacts — issues that are practically invisible to manual auditing.