yeok/faithfulness-esnli-Qwen_Qwen3-8B-random-insertion
Viewer • Updated • 6k • 5
c
yeok
AI & ML interests
None yet
Organizations
None yet
yeok/faithfulness-ood-Qwen_Qwen3-8B-user_bias
Viewer • Updated • 4.48k • 6
yeok/faithfulness-train-Qwen_Qwen3-8B-user_bias
Viewer • Updated • 8.6k • 5
yeok/faithfulness-train-Qwen_Qwen3-8B-random_insertion
Viewer • Updated • 8.17k • 6
yeok/faithfulness-ood-Qwen_Qwen3-8B-random_insertion
Viewer • Updated • 3.46k • 6
yeok/faithfulness-ood-meta-llama_Llama-3.1-8B-Instruct-user_bias
Viewer • Updated • 4.77k • 9
yeok/faithfulness-train-meta-llama_Llama-3.1-8B-Instruct-user_bias
Viewer • Updated • 8.7k • 5
yeok/faithfulness-train-meta-llama_Llama-3.1-8B-Instruct-random_insertion
Viewer • Updated • 7.98k • 6
yeok/faithfulness-ood-meta-llama_Llama-3.1-8B-Instruct-random_insertion
Viewer • Updated • 3.23k • 6
yeok/rl-faithfulness-results
Viewer • Updated • 108 • 10
yeok/faithfulness-comve-meta-llama_Llama-3.1-8B-Instruct-user-bias
Viewer • Updated • 2.61k • 6
yeok/faithfulness-comve-meta-llama_Llama-3.1-8B-Instruct-random-insertion
Viewer • Updated • 2.27k • 5
yeok/faithfulness-comve-old
Viewer • Updated • 11k • 6
yeok/faithfulness-comve-debug_1_wrong
Viewer • Updated • 11k • 4
yeok/faithfulness-comve-debug-backup-2
Viewer • Updated • 11k • 5
yeok/meta-llama_Llama-meta-llama_Llama-3.1-8B-Instruct-random-insertion
Viewer • Updated • 5.84k • 5
yeok/meta-llama_Llama-meta-llama_Llama-3.1-8B-Instruct-user-bias
Viewer • Updated • 2.16k • 4
yeok/faithfulness-esnli-debug_1-Qwen_Qwen3-8B-rl-sft-prompts-random-insertion-balanced
Viewer • Updated • 15.6k • 5
yeok/faithfulness-esnli-debug_1-meta-llama_Llama-3.1-8B-Instruct-user-bias
Viewer • Updated • 36.1k • 6
yeok/faithfulness-esnli-debug_1-meta-llama_Llama-3.1-8B-Instruct-random-insertion
Viewer • Updated • 11.6k • 6
yeok/faithfulness-esnli-debug_1-Qwen_Qwen3-8B-sft-prompts-user-bias-balanced
Viewer • Updated • 47.1k • 5
yeok/faithfulness-esnli-debug_1-Qwen_Qwen2.5-7B-Instruct-sft-prompts-user-bias-balanced
Viewer • Updated • 8.97k • 5
yeok/faithfulness-esnli-debug_1-Qwen_Qwen2.5-7B-Instruct-rl-sft-prompts-random-insertion-balanced
Viewer • Updated • 14.5k • 4
yeok/debug-with-rewards-128
Viewer • Updated • 128 • 5
yeok/debug-with-rewards
Preview • Updated • 5
yeok/faithfulness-combined-strategy_qa-esnli-random_insertion
Viewer • Updated • 17.8k • 5
yeok/faithfulness-combined-strategy_qa-esnli-user_bias
Viewer • Updated • 40.4k • 6
yeok/faithfulness-strategy_qa-debug_1-sft-prompts-user-bias-balanced
Viewer • Updated • 2.23k • 4
yeok/faithfulness-strategy_qa-debug_1-sft-prompts-random-insertion-balanced
Viewer • Updated • 1.11k • 5
yeok/faithfulness-comve-debug_1-sft-prompts-user-bias-balanced
Viewer • Updated • 9.79k • 5