S1-Evo: Experience-Guided Evidence Competition Attacks on Typed System-1 Decision Models
cs.AI
Submitted: 2026-11-12
Updated: 2026-11-13
Code: https://github.com/jaredpalmer/kev
Terminology
Sources
- Jailbreaking Black Box Large Language Models in Twenty Queries
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision
- FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Efficient Guided Generation for Large Language Models
- Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
- JevOut: Natural Context Can Flip Decision Models
- Universal and Transferable Adversarial Attacks on Aligned Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents