BenchPreS: A Benchmark for Context-Aware Personalized Prefer BenchPreS evaluates whether persistent-memory LLMs can selectively apply or suppress stored user preferences based on communicative context. sangyon/BenchPreS Viewer • Updated Mar 20 • 390 • 89 • 17
R-TOFU: Unlearning in Large Reasoning Models sangyon/R-TOFU Viewer • Updated Jun 27, 2025 • 10.6k • 178 sangyon/LRM-target 8B • Updated Apr 20, 2025 • 77
DUSK: Do not Unlearn Shared Knowledge AI-ISL/DUSK-target 8B • Updated Apr 26, 2025 • 3 • 3 AI-ISL/DUSK-retrain 8B • Updated May 3, 2025 • 6 AI-ISL/DUSK Viewer • Updated May 16, 2025 • 856 • 170 • 2
Rainbow-Padding We introduce Rainbow Padding, a cyclic multi-token padding scheme that eliminates early termination and restores length robustness in instruction-tune quasar529/rainbow-padding-llada Text Generation • Updated Oct 9, 2025 • 3 • 1
Model with SAFEPATH AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP Text Generation • 8B • Updated May 27, 2025 • 57 AI-ISL/DeepSeek-R1-Distill-Llama-8B-SP Text Generation • 8B • Updated May 27, 2025 • 57 • AI-ISL/HarmChain Viewer • Updated May 27, 2025 • 3.72k • 34 • 2
BenchPreS: A Benchmark for Context-Aware Personalized Prefer BenchPreS evaluates whether persistent-memory LLMs can selectively apply or suppress stored user preferences based on communicative context. sangyon/BenchPreS Viewer • Updated Mar 20 • 390 • 89 • 17
Rainbow-Padding We introduce Rainbow Padding, a cyclic multi-token padding scheme that eliminates early termination and restores length robustness in instruction-tune quasar529/rainbow-padding-llada Text Generation • Updated Oct 9, 2025 • 3 • 1
R-TOFU: Unlearning in Large Reasoning Models sangyon/R-TOFU Viewer • Updated Jun 27, 2025 • 10.6k • 178 sangyon/LRM-target 8B • Updated Apr 20, 2025 • 77
Model with SAFEPATH AI-ISL/DeepSeek-R1-Distill-Qwen-7B-SP Text Generation • 8B • Updated May 27, 2025 • 57 AI-ISL/DeepSeek-R1-Distill-Llama-8B-SP Text Generation • 8B • Updated May 27, 2025 • 57 • AI-ISL/HarmChain Viewer • Updated May 27, 2025 • 3.72k • 34 • 2
DUSK: Do not Unlearn Shared Knowledge AI-ISL/DUSK-target 8B • Updated Apr 26, 2025 • 3 • 3 AI-ISL/DUSK-retrain 8B • Updated May 3, 2025 • 6 AI-ISL/DUSK Viewer • Updated May 16, 2025 • 856 • 170 • 2
