Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Aerosta
/
rewardhackwatch
like
1
Text Classification
Transformers
Safetensors
PyTorch
custom
English
distilbert
reward-hacking
ai-safety
misalignment-detection
llm-safety
alignment
Eval Results (legacy)
arxiv:
2511.18397
arxiv:
2503.11926
License:
mit
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
rewardhackwatch
/
special_tokens_map.json
Aerosta
Upload folder using huggingface_hub
4043f5b
verified
5 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
125 Bytes
{
"cls_token"
:
"[CLS]"
,
"mask_token"
:
"[MASK]"
,
"pad_token"
:
"[PAD]"
,
"sep_token"
:
"[SEP]"
,
"unk_token"
:
"[UNK]"
}