4 papers
Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
Haoming Wen, Shi Chen, Qingyu Shi +4
Malicious finetuning attacks pose a major safety threat against open-weight large language models (LLMs). However, existing alignment-stage defenses provide limited protection agai…
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…
Differences in Text Generated by Diffusion and Autoregressive Language Models
Zeyang Zhang, Chengwei Liang, Xingyan Chen +4
Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated text remain underexplored. We…
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…