Haritz Puerto
haritzpuerto
AI & ML interests
Reasoning in LLMs, Question Answering
Recent Activity
upvoted
a
paper
7 days ago
ProPILE: Probing Privacy Leakage in Large Language Models
updated
a collection
7 days ago
š Papers
Organizations
haritzpuerto's activity
posted
an
update
6 days ago
upvoted
a
paper
7 days ago
posted
an
update
7 days ago
Post
1437
I'm excited to announce that my internship paper at Parameter Lab was accepted to Findings of #NAACL2025 š
TLDR: Stating an LLM was trained on a sentence might not be possible š„ , but it is possible for large enough amounts of tokens, such as long documents or multiple documents! š¤Æ
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models (2411.00154)
š https://github.com/parameterlab/mia-scaling
TLDR: Stating an LLM was trained on a sentence might not be possible š„ , but it is possible for large enough amounts of tokens, such as long documents or multiple documents! š¤Æ
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models (2411.00154)
š https://github.com/parameterlab/mia-scaling
upvoted
an
article
about 2 months ago
Article
EuroLLM-9B
By
ā¢
ā¢
106