NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
25 results for “keyword:"llm unlearn"” in ICLR 2027. 3 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]FedCoDS: Federated LLM Unlearning by Coupling Knowledge Distillation with Likelihood Suppression▲3.8k2.50
[PDF]ARC-Unlearn: Blast-Radius-Aware LLM Unlearning via Agentic Retain-Set Synthesis and Adjacent-Retain NPO▼1.2k1.67
[PDF]Towards Substantive LLM Unlearning: Robust Evaluation and Expression-Insensitive Metric▲5.4k3.00
[PDF]CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation▲482.75
[PDF]UnlearnBench: A Clean and Controllable Benchmark for Fine-Grained and Compositional LLM Unlearning▼1.3k1.75