3 papers
cs.HC2026
Stay or Stray - A Dynamical Systems Viewpoint of Popularity Bias
Sarvesh Shashidhar, Lankireddy Prabhat, Arpit Agarwal +3
Popularity bias in recommendation systems arises when a majority user class generates disproportionate interaction data, causing the system to increasingly favour it while degradin…
cs.HC2026
Exploring Re-inforcement Learning via Human Feedback under User Heterogeneity
Sarvesh Shashidhar, Abhishek Mishra, Madhav Kotecha
Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to a…
cs.AI2025
Inducing Robustness in a 2 Dimensional Direct Preference Optimization Paradigm
Sarvesh Shashidhar, Ritik, Nachiketa Patil +2
Direct Preference Optimisation (DPO) has emerged as a powerful method for aligning Large Language Models (LLMs) with human preferences, offering a stable and efficient alternative…