https://arxiv.org/abs/2509.02563
AI & ML interests
AI security & privacy, algorithmic bias, foundations of ML
Recent Activity
This collection contains models described in the refusal token paper published in COLM 2025.
-
tomg-group-umd/zephyr-llama3-8b-sft-refusal-n-contrast
8B • Updated • 22 -
tomg-group-umd/zephyr-llama3-8b-sft-refusal-n-contrast-multiple-tokens
8B • Updated • 4.51k -
tomg-group-umd/zephyr-llama3-8b-sft-refusal-n-contrast-single-token
8B • Updated • 26 • 1 -
tomg-group-umd/zephyr-llama3-8b-sft-no-refusal-messages
8B • Updated • 13
https://arxiv.org/abs/2509.02563
This collection contains models described in the refusal token paper published in COLM 2025.
-
tomg-group-umd/zephyr-llama3-8b-sft-refusal-n-contrast
8B • Updated • 22 -
tomg-group-umd/zephyr-llama3-8b-sft-refusal-n-contrast-multiple-tokens
8B • Updated • 4.51k -
tomg-group-umd/zephyr-llama3-8b-sft-refusal-n-contrast-single-token
8B • Updated • 26 • 1 -
tomg-group-umd/zephyr-llama3-8b-sft-no-refusal-messages
8B • Updated • 13
models
138
tomg-group-umd/DynaGuard-1.7B
Text Generation
•
2B
•
Updated
•
89
•
2
tomg-group-umd/DynaGuard-4B
Text Generation
•
4B
•
Updated
•
94
•
2
tomg-group-umd/DynaGuard-8B
Text Generation
•
8B
•
Updated
•
282
•
12
tomg-group-umd/step-00010720-baseline_2_0
Text Generation
•
4B
•
Updated
•
12
tomg-group-umd/LoRI-D_nlu_llama3_rank_64
Text Generation
•
Updated
•
11
tomg-group-umd/LoRI-D_safety_llama3_rank_64
Text Generation
•
Updated
•
11
tomg-group-umd/LoRI-D_nlu_llama3_rank_32
Text Generation
•
Updated
•
9
tomg-group-umd/LoRI-S_nlu_llama3_rank_32
Text Generation
•
Updated
•
9
tomg-group-umd/LoRI-S_nlu_llama3_rank_64
Text Generation
•
Updated
•
10
tomg-group-umd/LoRI-D_code_llama3_rank_32
Text Generation
•
Updated
•
12
datasets
28
tomg-group-umd/DynaBench
Viewer
•
Updated
•
140k
•
116
•
2
tomg-group-umd/huginn-dataset
Viewer
•
Updated
•
274M
•
2.97k
•
6
tomg-group-umd/pixelprose-jsons
Preview
•
Updated
•
39
tomg-group-umd/gemstones_data_order_sequential
Viewer
•
Updated
•
170M
•
508
tomg-group-umd/gemstones_data_order_parallel
Viewer
•
Updated
•
170M
•
616
tomg-group-umd/argus
Viewer
•
Updated
•
500
•
219
•
1
tomg-group-umd/morse-500
Updated
•
6
tomg-group-umd/fictionalqa_reformatted_triviaqa
Viewer
•
Updated
•
16.4k
•
140
tomg-group-umd/fictionalqa_training_splits
Viewer
•
Updated
•
107k
•
226
tomg-group-umd/fictionalqa
Viewer
•
Updated
•
31.7k
•
98
•
2