TULIP: Targeted LLM Unlearning at Layers Identified Per-input
cs.AI
Submitted: 2026-09-28
Updated: 2026-10-14
Sources
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Who's Harry Potter? Approximate Unlearning in LLMs
- The Llama 3 Herd of Models
- Verbalizable Representations Form a Global Workspace in Language Models
- How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
- Qwen2.5 Technical Report
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Qwen3 Technical Report
Related papers
- 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
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems