Karim Galliamov

2 accepted papers

2026

Concepts' Information Bottleneck Models

Karim Galliamov, Syed M Ahsan Kazmi, Adil Khan, Adín Ramírez Rivera

ICLR 2026poster

Concept Bottleneck Models (CBMs) aim to deliver interpretable predictions by routing decisions through a human-understandable concept layer, yet they often suffer reduced accuracy and concept leakage that undermines faithfulness. We introduce an explicit Information Bottleneck regularizer on the con…

Cited by 0 Source ↗Scholar ↗

2025

Enhancing RLHF with Human Gaze Modeling

Karim Galliamov, Ivan Titov, Ilya Pershin

EMNLP 2025

Reinforcement Learning from Human Feedback (RLHF) aligns language models with human preferences but faces efficiency challenges. We explore two approaches leveraging human gaze prediction to enhance RLHF: (1) gaze-aware reward models and (2) gaze-based distribution of sparse rewards at token level.

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗