6 papers
Code Comprehension then Auditing for Unsupervised LLM Evaluation
Bhrij Patel, Souradip Chakraborty, Mengdi Wang +2
Large Language Models (LLMs) for unsupervised code correctness evaluation have recently gained attention because they can judge if code runs as intended without requiring reference…
Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy +6
Recent trends in test-time scaling for reasoning models (e.g., OpenAI o1, DeepSeek R1) have led to a popular belief that extending thinking traces using prompts like "Wait" or "Let…
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…
Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment
Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh +7
With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that des…
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…