Adversarial Goodhart RLHF

classroom

AI & ML interests

None defined yet.

AdversarialRLHF 's datasets 43

AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiepropallprefix

Viewer • Updated Apr 27, 2025 • 130k • 24

AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieallprefix

Viewer • Updated Apr 27, 2025 • 130k • 53

AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_trained_allprefix

Viewer • Updated Apr 27, 2025 • 300 • 14

AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_trained

Viewer • Updated Apr 27, 2025 • 300 • 16

AdversarialRLHF/summarize_from_feedback_tldr_3_filtered_oai_preprocessing_1706381144_allprefix

Viewer • Updated Apr 27, 2025 • 130k • 69

AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieboth

Viewer • Updated Apr 26, 2025 • 130k • 27

AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojieprefix

Viewer • Updated Apr 26, 2025 • 130k • 20

AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_logprobs_cond3emojiesuffix

Viewer • Updated Apr 26, 2025 • 130k • 16

AdversarialRLHF/sffop_1706381144_410msft_relabel_pythia6.9b_3emojieprefix_randomize

Viewer • Updated Apr 24, 2025 • 130k • 25

AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_relabel_pythia6.9b_logprobs

Viewer • Updated Apr 24, 2025 • 130k • 57

AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft_relabel_pythia6.9b

Viewer • Updated Apr 23, 2025 • 130k • 38

AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_relabel_pythia6.9b_3emojieprefix_chosen

Viewer • Updated Apr 22, 2025 • 177k • 20

AdversarialRLHF/summarize_from_feedback_oai_preprocessing_1706381144_410msft

Viewer • Updated Apr 22, 2025 • 130k • 30