Epistemic Policy Divergence in Multi-Turn LLM Contamination: A Protocol-Gradient Investigation
cs.CL
Submitted: 2026-09-28
Updated: 2026-10-07
Code: https://github.com/fahrellgiovanny/epistemic-policy-divergence
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States
- GLM: General Language Model Pretraining with Autoregressive Blank Infilling
- Trojan Horse Prompting: Jailbreaking Conversational Multimodal Models by Forging Assistant Message
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
- Gemini: A Family of Highly Capable Multimodal Models
- Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection
- ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
- A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models
- Survey of Hallucination in Natural Language Generation
- When AI Meets the Web: Prompt Injection Risks in Third-Party AI Chatbot Plugins
- HaluEval: A Large-Scale Hallucination Evaluation Benchmark for Large Language Models
- CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges
- MemOS: A Memory OS for AI System
- Momento: Evaluating Persistent Memory and Reasoning with Multi-Session Agentic Conversations
- MemGPT: Towards LLMs as Operating Systems
- Ignore Previous Prompt: Attack Techniques For Language Models
- Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models
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