#model-utility News & Analysis

4 articles tagged with #model-utility. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles

AINeutralarXiv – CS AI · Jun 256/10

🧠

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning

Researchers introduce DiPO (Distribution Preference Optimization), a novel algorithm for LLM unlearning that operates at the token distribution level rather than full response level. The method addresses limitations in existing approaches like NPO by constructing preference signals through selective amplification of model logits, achieving superior performance on benchmark tests while maintaining model utility.

AIBullisharXiv – CS AI · Jun 236/10

🧠

OFMU: Optimization-Driven Framework for Machine Unlearning

Researchers propose OFMU, a bi-level optimization framework designed to enable large language models to selectively unlearn specific data without full retraining, addressing privacy and regulatory compliance needs. The method balances forgetting targeted information while maintaining model performance through hierarchical optimization with theoretical convergence guarantees.

AINeutralarXiv – CS AI · Jun 46/10

🧠

ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models

Researchers introduce ZeroUnlearn, a novel machine unlearning framework that efficiently removes sensitive information from large language models through knowledge re-mapping and representational orthogonality, rather than expensive retraining. The method preserves overall model utility while selectively unlearning harmful data in few-shot settings, addressing critical privacy and safety concerns in LLMs.

AINeutralarXiv – CS AI · May 116/10

🧠

SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion

Researchers introduce SHRED, a machine unlearning method for large language models that removes memorized private or copyrighted data without requiring a curated retain set of examples. By selectively demoting logits of high-information tokens while preserving model utility through self-distillation, SHRED achieves superior trade-offs between forgetting efficacy and performance compared to existing retain-set-dependent approaches.