Awesome Large Language Models
📄
Papers
🧭
Topics
🔥
Trending
🗺️
Map
🏆
Leaderboards
🎓
Learn
🤖
Ask AI
⋯
More
👥
Authors
📚
Reading Packs
📊
Datasets
🛠️
Tools
📰
News
📝
Blogs
✉️
Newsletter
🎯
Research Radar
🔖
Saved
+ Add Paper
☾
☀
← authors
·
overview
Loading author…
🤖
Ask AI
Kellin Pelrine — most-cited papers & profile · Large Language Models
← authors
·
overview
Kellin Pelrine
10
papers ·
5
citations ·
4
h-index
Laboratorio De Aplicaciones Farmacodinamicas (Spain) · McGill University
Google Scholar ↗
Semantic Scholar ↗
OpenAlex ↗
Most-cited papers
Exploiting Novel GPT-4 APIs
2023 · 3 citations
Scaling Trends for Data Poisoning in LLMs
2024 · 1 citations
Accidental Vulnerability: Factors In Fine-tuning That Shift Model Safeguards
2025
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
2026
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
2026
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
2025
The Structural Safety Generalization Problem
2025
Emerging Vulnerabilities in Frontier Models: Multi-Turn Jailbreak Attacks
2024
Top co-authors
Adam Gleave
· 1
Bijean Ghafouri
· 1
Hikaru Tsujimura
· 1
Jacob-Junqi Tian
· 1
James Zhou
· 1
Jean-Fran\c{c}ois Godbout
· 1
Lukas Struppek
· 1
Mayank Goel
· 1
Pratheeksha Nair
· 1
Reihaneh Rabbany
· 1
Shahrad Mohammadzadeh
· 1
Sukanya Krishna
· 1
Topics
Vulnerability Detection
LLM Security
Adversarial ML
Threat Intelligence