model outputs

5 papers

• Distributional Training Data Attribution: What do Influence Functions Sample?
• ExPO: Unlocking Hard Reasoning with Self-Explanation-Guided Reinforcement Learning
• Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
• The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples
• Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference