Xudong Han

Balancing out Bias: Achieving Fairness Through Training Reweighting.

2021 · arXiv (Cornell University)

Bias in natural language processing arises primarily from models learning characteristics of the author such as gender and race when modelling tasks such as sentiment and syntactic parsing. This problem manifests as disparities in error …

Demystifying Instruction Mixing for Fine-tuning Large Language Models

2024

Renxi Wang, Haonan Li, Minghao Wu, Yuxia Wang, Xudong Han, Chiyu Zhang, Timothy Baldwin. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop). 2024.

Learning to Align, Aligning to Learn: A Unified Approach for Self-Optimized Alignment

2025 · arXiv (Cornell University)

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is constrained by offline policy trajectory. In contrast, …