4 papers · 1 filter
LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
James Beetham, Souradip Chakraborty, Mengdi Wang +3
Jailbreak attacks expose vulnerabilities in safety-aligned LLMs by eliciting harmful outputs through carefully crafted prompts. Existing methods rely on discrete optimization or tr…
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
Souradip Chakraborty, Sujay Bhatt, Udari Madhushani Sehwag +7
Alignment of Large Language models (LLMs) is crucial for safe and trustworthy deployment in applications. Reinforcement learning from human feedback (RLHF) has emerged as an effect…
MaxMin-RLHF: Alignment with Diverse Human Preferences
Souradip Chakraborty, Jiahao Qiu, Hui Yuan +5
Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data. However, such an ap…
Transfer Q Star: Principled Decoding for LLM Alignment
Souradip Chakraborty, Soumya Suvra Ghosal, Ming Yin +4
Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billi…