Toward Measuring Structural Drift in LLM Communication Loops

arXiv:2604.13061 · cs.CL, cs.AI · Submitted 2026-03-18 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-03-18

Updated: 2026-09-23

Terminology

• Consistency — 30× in this paper · explained in 3 episodes
• Cosine Similarity — 11× in this paper · explained in 3 episodes
• LLM-as-a-Judge — 9× in this paper · explained in 3 episodes
• Digital Twin — 8× in this paper · explained in 4 episodes
• Embeddings — 8× in this paper · explained in 2 episodes
• Information Digital Twin — 8× in this paper
• Hallucination — 7× in this paper · explained in 3 episodes
• Grounding — 4× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 2× in this paper
• Hallucination Detection — 2× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 2× in this paper
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Perplexity — 2× in this paper · explained in 3 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• LLM judge — 1× in this paper · explained in 2 episodes

Sources

• On the Opportunities and Risks of Foundation Models
• A Survey on LLM-as-a-Judge
• A Mathematical Theory of Agency and Intelligence
• Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
• Language Models (Mostly) Know What They Know
• LLMs Get Lost In Multi-Turn Conversation
• Evaluating Scoring Bias in LLM-as-a-Judge
• Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
• NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
• On Hallucination and Predictive Uncertainty in Conditional Language Generation

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