Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
Siyuan Liu, Tinghong Chen, Xinghan Li +2
Data selection during supervised fine-tuning (SFT) can critically change the behavior of large language models (LLMs). Although existing work has studied the effect of selecting da…
cs.LG2019
Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?
Tianxing He, Jingzhao Zhang, Zhiming Zhou +1
Exposure bias has been regarded as a central problem for auto-regressive language models (LM). It claims that teacher forcing would cause the test-time generation to be incremental…