UnlearningSoup: Is Repeated Tuning Necessary for Large Language Model Unlearning?
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Sources
- GPT-4 Technical Report
- On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment
- Per-parameter Task Arithmetic for Unlearning in Large Language Models
- Who's Harry Potter? Approximate Unlearning in LLMs
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- The Llama 3 Herd of Models
- Textbooks Are All You Need II: phi-1.5 technical report
- LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction
- DeepSeek-V3 Technical Report
- Eight Methods to Evaluate Robust Unlearning in LLMs
- Fast Exact Unlearning for In-Context Learning Data for LLMs
- Scalable Extraction of Training Data from (Production) Language Models
- Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
- Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
- Gemini: A Family of Highly Capable Multimodal Models
- Guardrail Baselines for Unlearning in LLMs
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- Zephyr: Direct Distillation of LM Alignment
- Editing Large Language Models: Problems, Methods, and Opportunities
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks