Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs

• URL: http://arxiv.org/abs/2606.12385v1
• Date: Wed, 10 Jun 2026 17:47:59 GMT
• Title: Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
• Abstract summary: We introduce ModSleuth, a system that reconstructs dependency graphs from public artifacts with source-grounded evidence.<n>Applying ModSleuth to four public-artifact-rich LLM releases, we recover 1,060 source-verified dependencies and construct large-scale dependency graphs.<n>These graphs reveal multi-hop license obligations, train-evaluation coupling, discrepancies between released and training-time artifacts, and documentation inconsistencies.
• Score: 21.170181670676566
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern LLM training pipelines increasingly rely on other models to generate data, filter corpora, judge outputs, and guide development decisions. These dependencies are recursive: a model may depend on an upstream artifact whose own dependencies are documented only in separate releases and artifacts. As a result, the full dependency structure is fragmented across heterogeneous public artifacts, with complexity and recursive depth far outpacing humans' ability to trace. We introduce ModSleuth, an agentic system that recursively reconstructs LLM dependency graphs from public artifacts with source-grounded evidence. We find that the primary challenge is no longer information extraction, but defining what constitutes a dependency and reconciling artifact references across inconsistent documentation. We address these challenges through a formalization that distinguishes direct and indirect dependencies, represents heterogeneous pipeline roles through operation-centered relationships, and resolves artifact identities across names, versions, and repositories. Applying ModSleuth to four public-artifact-rich LLM releases, we recover 1,060 source-verified dependencies and construct large-scale dependency graphs of modern LLM development. These graphs reveal multi-hop license obligations, train-evaluation coupling, discrepancies between released and training-time artifacts, and documentation inconsistencies that would otherwise be difficult to uncover. We release ModSleuth and the resulting dependency graphs to support transparent analysis of the increasingly complex ecosystems underlying modern LLMs.

Related papers

• An Evidence-First Multi-LLM Framework for Auditable Critical-Infrastructure Dependency Modeling [0.0]
  Critical-infrastructure knowledge is distributed across heterogeneous, incomplete, and weakly structured evidence.<n>We present an evidence-first multi-LLM framework for constructing Infrastructure Knowledge Bases (IKBs) and Infrastructure Dependency Graphs (IDGs) from heterogeneous infrastructure documentation.
  arXiv  Detail & Related papers  (2026-09-11T02:33:13Z)
• Beyond Repository Boundaries: Cross-Repository Graph Retrieval for Code Generation [15.95046921483187]
  CrossCoder is a cross-repository code generation framework that explicitly incorporates external libraries into the retrieval context.<n>We show that CrossCoder consistently improves both functional correctness (up to 6.3% on pass@1) and robustness to dependency-version changes.
  arXiv  Detail & Related papers  (2026-09-09T10:14:14Z)
• Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation [8.490743624223972]
  We propose DyRetriever, an efficient context retrieval method via partial dependency graphs.<n>We integrate DyRetriever with a similarity-based code retriever to build DyCoder and evaluate it on CoderEval and DevEval.
  arXiv  Detail & Related papers  (2026-08-03T09:00:49Z)
• RepoReasoner: Evaluating Repository-Level Code Reasoning Ability of Long-Context Language Models [54.53236295237077]
  We introduce RepoReasoner, a benchmark for evaluating repository-level code reasoning.<n> Output Prediction measures fine-grained, stateful execution reasoning across files.<n>Call Chain Prediction evaluates high-level architectural dependency understanding under noisy context.
  arXiv  Detail & Related papers  (2026-07-28T17:12:41Z)
• Beyond Textual Repository Exploration: Dual-Modal Structural Reasoning for Agentic Issue Resolution [24.103118645295655]
  CouplingVIEW brings visual reasoning into repository exploration for issue-resolution agents.<n>VIEW consistently improves issue-resolution performance across different agent architectures and model families.
  arXiv  Detail & Related papers  (2026-07-02T09:23:48Z)
• Large Language Model Sourcing: A Survey [84.63438376832471]
  Large language models (LLMs) have revolutionized artificial intelligence, shifting from supporting objective tasks to empowering subjective decision-making.<n>Due to the black-box nature of LLMs and the human-like quality of their generated content, issues such as hallucinations, bias, unfairness, and copyright infringement become significant.<n>This survey presents a systematic investigation into provenance tracking for content generated by LLMs, organized around four interrelated dimensions.
  arXiv  Detail & Related papers  (2025-10-11T10:52:30Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router [57.28685457991806]
  DeepSieve is an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router.<n>Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design.
  arXiv  Detail & Related papers  (2025-07-29T17:55:23Z)
• LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning [15.20947984949809]
  We propose ColaUntangle, a new collaborative consultation framework for commit untangling.<n>ColaUntangle integrates Large Language Model (LLM)-driven agents in a multi-agent architecture.<n>We evaluate ColaUntangle on two widely-used datasets (1,612 C# and 14k Java tangled commits)
  arXiv  Detail & Related papers  (2025-07-22T09:42:13Z)
• Beyond Isolated Dots: Benchmarking Structured Table Construction as Deep Knowledge Extraction [80.88654868264645]
  Arranged and Organized Extraction Benchmark designed to evaluate ability of large language models to comprehend fragmented documents.<n>AOE includes 11 carefully crafted tasks across three diverse domains, requiring models to generate context-specific schema tailored to varied input queries.<n>Results show that even the most advanced models struggled significantly.
  arXiv  Detail & Related papers  (2025-07-22T06:37:51Z)
• Large Language Models are Good Relational Learners [55.40941576497973]
  We introduce Rel-LLM, a novel architecture that utilizes a graph neural network (GNN)- based encoder to generate structured relational prompts for large language models (LLMs)<n>Unlike traditional text-based serialization approaches, our method preserves the inherent relational structure of databases while enabling LLMs to process and reason over complex entity relationships.
  arXiv  Detail & Related papers  (2025-06-06T04:07:55Z)
• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• A Data Source Dependency Analysis Framework for Large Scale Data Science Projects [0.0]
  Data source dependency hell refers to the central role played by data and its unique quirks that often lead to unexpected failures of machine learning models. We present an automated dependency mapping framework that allows MLOps engineers to monitor the whole dependency map of their models in a fast paced engineering environment.
  arXiv  Detail & Related papers  (2022-12-15T16:34:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.