aiXamine: Simplified LLM Safety and Security
Authors: Fatih Deniz, Dorde Popovic, Yazan Boshmaf, Euisuh Jeong, Minhaj Ahmad, Sanjay Chawla, Issa Khalil | Published: 2025-04-21 | Updated: 2025-04-23
Alignment
GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms
Authors: Sinan He, An Wang | Published: 2025-04-17
Personalized Attacks of Social Engineering in Multi-turn Conversations — LLM Agents for Simulation and Detection
Authors: Tharindu Kumarage, Cameron Johnson, Jadie Adams, Lin Ai, Matthias Kirchner, Anthony Hoogs, Joshua Garland, Julia Hirschberg, Arslan Basharat, Huan Liu | Published: 2025-03-18
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings
Authors: Weikai Lu, Hao Peng, Huiping Zhuang, Cen Chen, Ziqian Zeng | Published: 2025-02-18 | Updated: 2025-05-21
Generating Privacy-Preserving Personalized Advice with Zero-Knowledge Proofs and LLMs
Authors: Hiroki Watanabe, Motonobu Uchikoshi | Published: 2025-02-10 | Updated: 2025-04-24
SimPO: Simple Preference Optimization with a Reference-Free Reward
Authors: Yu Meng, Mengzhou Xia, Danqi Chen | Published: 2024-05-23 | Updated: 2024-11-01
KTO: Model Alignment as Prospect Theoretic Optimization
Authors: Kawin Ethayarajh, Winnie Xu, Niklas Muennighoff, Dan Jurafsky, Douwe Kiela | Published: 2024-02-02 | Updated: 2024-11-19
Self-Rewarding Language Models
Authors: Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, Jason Weston | Published: 2024-01-18 | Updated: 2024-02-08
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Authors: Hakan Inan, Kartikeya Upasani, Jianfeng Chi, Rashi Rungta, Krithika Iyer, Yuning Mao, Michael Tontchev, Qing Hu, Brian Fuller, Davide Testuggine, Madian Khabsa | Published: 2023-12-07
A General Theoretical Paradigm to Understand Learning from Human Preferences
Authors: Mohammad Gheshlaghi Azar, Mark Rowland, Bilal Piot, Daniel Guo, Daniele Calandriello, Michal Valko, Rémi Munos | Published: 2023-10-18 | Updated: 2023-11-22