BOLT: Bootstrap Long Chain-of-Thought in Language Models without Distillation Paper • 2502.03860 • Published Feb 6 • 24
Reward-Guided Speculative Decoding for Efficient LLM Reasoning Paper • 2501.19324 • Published Jan 31 • 38
Offline Reinforcement Learning for LLM Multi-Step Reasoning Paper • 2412.16145 • Published Dec 20, 2024 • 38
MathHay: An Automated Benchmark for Long-Context Mathematical Reasoning in LLMs Paper • 2410.04698 • Published Oct 7, 2024 • 13
cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_gemma-2b_1of4_iter1_bs128_lr1e-5_conf-0.7_slic Viewer • Updated Jul 25, 2024 • 72.1k • 52
cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_gemma-2b_1of4_iter1_bs128_lr1e-5_conf-0.7_slic Viewer • Updated Jul 25, 2024 • 71.9k • 47
cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_gemma-2b_1of4_iter1_bs128_lr1e-5_conf-0.7_slic Viewer • Updated Jul 25, 2024 • 72.4k • 48
cornfieldrm/pair-preference-dataset-700K_subset-4-of-4_gemma-2b_1of4_iter1_bs128_lr1e-5_conf-0.7 Viewer • Updated Jul 25, 2024 • 72.1k • 63
cornfieldrm/pair-preference-dataset-700K_subset-3-of-4_gemma-2b_1of4_iter1_bs128_lr1e-5_conf-0.7 Viewer • Updated Jul 25, 2024 • 71.9k • 55
cornfieldrm/pair-preference-dataset-700K_subset-2-of-4_gemma-2b_1of4_iter1_bs128_lr1e-5_conf-0.7 Viewer • Updated Jul 25, 2024 • 72.4k • 52
cornfieldrm/pair-preference-dataset-700K_subset-15-out-of-16_llama3-8b-it_1-of-16_iter_4_slic Viewer • Updated Jun 13, 2024 • 398k • 63
cornfieldrm/pair-preference-dataset-700K_subset-15-out-of-16_llama3-8b-it_1-of-16_iter_4 Viewer • Updated Jun 13, 2024 • 398k • 82
cornfieldrm/pair-preference-dataset-700K_subset-1-out-of-16_slic Viewer • Updated Jun 10, 2024 • 43.7k • 91
cornfieldrm/pair-preference-dataset-700K_subset-15-out-of-16_standard Viewer • Updated Jun 10, 2024 • 656k • 114
cornfieldrm/pair-preference-dataset-700K_subset-1-out-of-16_standard Viewer • Updated Jun 10, 2024 • 43.7k • 62
cornfieldrm/pair-preference-dataset-700K_subset-7-out-of-8_gemma-2b-it_1-of-8_slic Viewer • Updated Jun 10, 2024 • 68.6k • 61
cornfieldrm/pair-preference-dataset-700K_subset-7-out-of-8_gemma-2b-it_1-of-8 Viewer • Updated Jun 10, 2024 • 68.6k • 53
cornfieldrm/pair-preference-dataset-700K_subset-1-out-of-2_direct_slic Viewer • Updated Jun 10, 2024 • 350k • 56