Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
Open to Work
20.9
TFLOPS
9
26
238
P.M.SALMAN KHAN
salmankhanpm
Follow
venturespace's profile picture
Edge-Quant's profile picture
jorgemunozl's profile picture
16 followers
ยท
257 following
https://salmankhanpm.me
salmankhanpm154
SALMANKHANPM
salmankhanpm786
AI & ML interests
NLP - LLM - AI SAFETY
Recent Activity
reacted
to
MikeDoes
's
post
with โค๏ธ
about 18 hours ago
What happens when PII masking is treated as a trainable behavior, not just a detection task? A new reinforcement learning environment tackles this question using a dataset derived from ai4privacy/open-pii-masking-500k-ai4privacy, transformed into a verifier-based training and evaluation setup. Instead of evaluating PII masking as a one-off redaction step, this environment frames privacy as something models must consistently optimize for under feedback. The task requires models to correctly identify sensitive spans, replace them with [PII] tags, and comply with strict output formatting โ all scored through explicit reward signals. To make this realistic, the author filtered and normalized the dataset to focus on US-English examples, ensuring consistent masking targets while preserving the structural diversity needed to expose failure modes. What's notable here isn't just the environment itself, but the shift in perspective. By turning PII masking into a reinforcement learning problem, privacy stops being a static rule and becomes a behavior models are trained to maintain even under optimization pressure. This is a strong example of how open privacy datasets can move beyond benchmarks and become infrastructure for new learning paradigms. ๐ Explore the PII Masking RL environment on Prime Intellect: https://app.primeintellect.ai/dashboard/environments/adamlucek/pii-masking
liked
a model
1 day ago
google/gemma-4-E2B
liked
a dataset
3 days ago
Ujjwal-Tyagi/ai-ml-foundations-book-collection
View all activity
Organizations
salmankhanpm
's models
6
Sort:ย Recently updated
salmankhanpm/build-tools
Updated
27 days ago
salmankhanpm/qwen-2.5-coder-classification-v2
Updated
29 days ago
salmankhanpm/qwen-2.5-coder-classification-sft
Updated
29 days ago
salmankhanpm/gemma3-tokenizer-telugu-preview
Updated
Oct 6, 2025
salmankhanpm/gemma-3-4b-it-ft
Image-Text-to-Text
โข
4B
โข
Updated
Apr 25, 2025
โข
1
salmankhanpm/lora_gemma-3-4b-bt
14.9M
โข
Updated
Apr 25, 2025
โข
10