LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_cot_only-seed_0 Text Generation • 0.6B • Updated Mar 17 • 102
LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_cot_only-seed_1 Text Generation • 0.6B • Updated Mar 16 • 150
LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_all_tokens-seed_2 Text Generation • 0.6B • Updated Mar 16 • 151
LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_all_tokens-seed_1 Text Generation • 0.6B • Updated Mar 16 • 162
LorenaYannnnn/general_reward-Qwen3-0.6B-baseline_all_tokens-seed_0 Text Generation • 0.6B • Updated Mar 16 • 236
LorenaYannnnn/sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_1 Text Generation • 0.6B • Updated Mar 16 • 135
LorenaYannnnn/sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_2 Text Generation • 0.6B • Updated Mar 16 • 142
LorenaYannnnn/sycophancy-Qwen3-0.6B-baseline_all_tokens-seed_0 Text Generation • 0.6B • Updated Mar 16 • 100
LorenaYannnnn/20260314-sycophancy-Qwen3-0.6B_grpo_baseline_cot_only_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 14 • 3
LorenaYannnnn/20260314-sycophancy-Qwen3-0.6B_grpo_baseline_output_only_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 14 • 3
LorenaYannnnn/20260314-Skywork_qwen_0.6B-Qwen3-0.6B_grpo_w_classmate_cl_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 14 • 3
LorenaYannnnn/20260314-Skywork_qwen_0.6B-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 14 • 34
LorenaYannnnn/20260308-length_only-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 8 • 78
LorenaYannnnn/20260308-length_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 8 • 28
LorenaYannnnn/20260306-confidence_only-Qwen3-0.6B_OURS_cl_llama_partial_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 8 • 28
LorenaYannnnn/20260306-confidence_only-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 8 • 84
LorenaYannnnn/20260306-confidence_only-Qwen3-0.6B_OURS_cl_self_partial_192000_episodes_seed_42 Text Generation • 0.6B • Updated Mar 8 • 81
LorenaYannnnn/20260301-unsafe_compliance-Qwen3-0.6B_grpo_baseline_192000_episodes_seed_42 Updated Mar 1
LorenaYannnnn/20260228-helpfulness-Qwen3-0.6B_grpo_OURS_seed_42_wo_warmup Text Generation • 0.6B • Updated Mar 1 • 15
LorenaYannnnn/20260228-helpfulness-Qwen3-0.6B_grpo_baseline_seed_42_wo_warmup Text Generation • 0.6B • Updated Feb 28 • 13
LorenaYannnnn/20260227-Qwen3-0.6B_sycophancy_grpo_baseline_192000_episodes_seed_42_wo_warmup Text Generation • 0.6B • Updated Feb 28 • 16
LorenaYannnnn/20260227-Qwen3-0.6B_compliance_w_warmup_grpo_baseline_192000_episodes_seed_42 Text Generation • 0.6B • Updated Feb 27 • 14
LorenaYannnnn/20260227-Qwen3-0.6B_compliance_w_warmup_grpo_OURS_192000_episodes_seed_42 Text Generation • 0.6B • Updated Feb 27 • 16
LorenaYannnnn/20260227-Qwen3-0.6B_sycophancy_OURS_grpo_192000_episodes_seed_42_wo_warmup Updated Feb 27
LorenaYannnnn/20260217-Qwen3-0.6B_grpo_sycophancy_warmup_4x_baseline_320000_episodes_seed_42 Text Generation • 0.6B • Updated Feb 23 • 12