-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 3 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 4 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 4
Kyle O'Brien PRO
Kyle1668
AI & ML interests
Interpretability, model editing, alignment
Recent Activity
updated
a model
10 days ago
EleutherAI/early-unlearning-weak-filter-ga-1-in-41-ga-lr-scale-0_001-gclip-0_5
updated
a model
10 days ago
EleutherAI/early-unlearning-no-interventions-baseline-gclip-0_5
updated
a model
10 days ago
EleutherAI/early-unlearning-no-interventions-baseline-gclip-0_5
Organizations
-
Improving Black-box Robustness with In-Context Rewriting
Paper • 2402.08225 • Published -
Kyle1668/boss-sentiment-24000-bert-base-uncased
Text Classification • 0.1B • Updated • 3 -
Kyle1668/boss-sentiment-bert-base-uncased
Text Classification • 0.1B • Updated • 4 -
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification • 0.1B • Updated • 4
models
27
Kyle1668/answerdotai-ModernBERT-large_20250111-002259
Text Classification
•
0.4B
•
Updated
•
5
Kyle1668/answerdotai-ModernBERT-large_20250111-224237
Text Classification
•
0.4B
•
Updated
•
3
Kyle1668/answerdotai-ModernBERT-large_20241230-093521
Text Classification
•
0.4B
•
Updated
•
3
Kyle1668/allenai-scibert_scivocab_uncased_20241230-091934
Text Classification
•
0.1B
•
Updated
•
3
Kyle1668/boss-toxicity-bert-base-uncased
Text Classification
•
0.1B
•
Updated
•
4
Kyle1668/ag-news-t5-large
0.7B
•
Updated
•
7
Kyle1668/ag-news-76800-bert-base-uncased
Text Classification
•
0.1B
•
Updated
•
111
Kyle1668/ag-news-38400-bert-base-uncased
Text Classification
•
0.1B
•
Updated
•
5
Kyle1668/ag-news-19200-bert-base-uncased
Text Classification
•
0.1B
•
Updated
•
1.01k
Kyle1668/ag-news-9600-bert-base-uncased
Text Classification
•
0.1B
•
Updated
•
4
datasets
9
Kyle1668/mmlu_auxiliary_train_formatted_cloze
Viewer
•
Updated
•
99.8k
•
9
Kyle1668/wmdp_bio_historical_bioweapons
Viewer
•
Updated
•
36
•
9
Kyle1668/mmlu_auxiliary_train_formatted
Viewer
•
Updated
•
99.8k
•
10
Kyle1668/phi_sae_training
Viewer
•
Updated
•
17.2M
•
34
Kyle1668/LLM-TTA-Cached-Rewrites
Viewer
•
Updated
•
986k
•
23
Kyle1668/LLM-TTA-Augmentation-Logs
Viewer
•
Updated
•
4.43M
•
5
Kyle1668/AG-Tweets
Viewer
•
Updated
•
7.6k
•
12
Kyle1668/BOSS-Robustness-Benchmark
Preview
•
Updated
•
5
Kyle1668/pythia-semantic-memorization-perplexities
Viewer
•
Updated
•
99.7M
•
85