The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection Detection
cs.LG, cs.AI, cs.CL, cs.CR
Submitted: 2026-08-26
Updated: 2026-10-06
Terminology
Sources
- Prompt Leakage effect and defense strategies for multi-turn LLM interactions
- Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution
- The Embedder's Dilemma: LLMs Are Better, but at What Cost?
- Decomposed Prompting: A Modular Approach for Solving Complex Tasks
- Prompt Injection attack against LLM-integrated Applications
- SPML: A DSL for Defending Language Models Against Prompt Attacks
- ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data
- Text Embeddings by Weakly-Supervised Contrastive Pre-training
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks