#data-attribution News & Analysis

2 articles tagged with #data-attribution. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AINeutralarXiv – CS AI · Jun 26/10

🧠

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

Researchers introduce GUDA, a machine unlearning-based method for attributing influence of training data groups to outputs in diffusion models. The approach approximates counterfactual scenarios without expensive full retraining, achieving ~100x speedup while more reliably identifying which artistic styles or object classes contributed to generated images compared to existing attribution methods.

🧠 Stable Diffusion

AINeutralarXiv – CS AI · Jun 16/10

🧠

De-attribute to Forget for LLM Unlearning

Researchers propose DareU, a novel LLM unlearning framework that uses data attribution rewards and reinforcement learning to remove training data influence from large language models. Unlike existing approaches that maximize loss on forget sets, this method reduces attribution scores to forgotten data owners, addressing critical issues of over-forgetting and model utility degradation.