4 papers
MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment
Tony Tu, Sayan Chakraborty, Ruomeng Xu +2
Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additively, optimization collapses o…
Toward Uncertainty Quantification in Modern Art
Tirtho Roy, Ushashi Bhattacharjee, Showrav Kumar Saha +3
Asked to animate the same modern artwork under different random seeds, a text to video model returns visibly different films, one reading per seed. Because modern art is ambiguous…
Improving the Safety and Trustworthiness of Medical AI via Multi-Agent Evaluation Loops
Zainab Ghafoor, Md Shafiqul Islam, Koushik Howlader +6
Large Language Models (LLMs) are increasingly applied in healthcare, yet ensuring their ethical integrity and safety compliance remains a major barrier to clinical deployment. This…
Towards Robust Offline Evaluation: A Causal and Information Theoretic Framework for Debiasing Ranking Systems
Seyedeh Baharan Khatami, Sayan Chakraborty, Ruomeng Xu +1
Evaluating retrieval-ranking systems is crucial for developing high-performing models. While online A/B testing is the gold standard, its high cost and risks to user experience req…