Finding Icebergs in Language-Model Workflow: Diagnosing Latent Structural Fragility with Stochastic Semantic Evidence Graphs

arXiv:2609.29703 · cs.CL, cs.IR, stat.ML · Submitted 2026-09-03 · Read on arXiv

cs.CL, cs.IR, stat.ML

Submitted: 2026-09-03

Updated: 2026-09-26

Terminology

• Provenance — 20× in this paper · explained in 3 episodes
• Calibration — 13× in this paper · explained in 7 episodes
• RAG — 8× in this paper · explained in 3 episodes
• Wasserstein Distance — 5× in this paper · explained in 4 episodes
• Ontology — 4× in this paper · explained in 2 episodes
• Alignment — 3× in this paper · explained in 1 episode
• Topological Order — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• External Validation — 2× in this paper · explained in 2 episodes
• Agent Interactions — 1× in this paper · explained in 1 episode
• Agentic AI — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 16 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• PROV-AGENT: Unified Provenance for Tracking AI Agent Interactions in Agentic Workflows
• Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation
• Qwen3 Technical Report
• Mistral 7B
• Calibrating Semantic Uncertainty from Observable Language-Model Probabilities
• Identification and Learning of Semantic Observation Kernels: Partial Observation, Uniform Recovery, & Minimax Limits

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering