Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
Tong Xie, Yuanhao Ban, Yunqi Hong +3
Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-unique, noisy, or misaligned with…
cs.LG2025
When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
Tong Xie, Andrew Bai, Yuanhao Ban +3
Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling is the Bradley-Terry (BT) loss, which…