arxiv:2508.20931
Amir
sahsaeedi
·
AI & ML interests
NLP, RLHF, Alignment
Recent Activity
authored
a paper
about 9 hours ago
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs'
Memorization
authored
a paper
about 9 hours ago
Triple Preference Optimization: Achieving Better Alignment with Less
Data in a Single Step Optimization
authored
a paper
about 9 hours ago
When "Competency" in Reasoning Opens the Door to Vulnerability:
Jailbreaking LLMs via Novel Complex Ciphers
Organizations
models
0
None public yet
datasets
0
None public yet