6 papers · 1 filter
Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models
Longxuan Yu, Shaorong Zhang, Yu Fu +3
Masked diffusion language models (MDLMs) re-predict every position at each denoising step, but standard samplers commit tokens once revealed, leaving this revision capability unuse…
DSL-LLaDA: Scaling Continuous Denoising to 8B Masked Diffusion LMs
Longxuan Yu, Yunshu Wu, Yu Fu +5
Discrete Masked diffusion language models generate text by iterative parallel decoding, but few-step decoding suffers from a tradeoff between length and quality: with a fixed step…
Thinking Out of Order: When Output Order Stops Reflecting Reasoning Order in Diffusion Language Models
Longxuan Yu, Yu Fu, Shaorong Zhang +4
Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reas…
TRAWL: Tensor Reduced and Approximated Weights for Large Language Models
Yiran Luo, Het Patel, Yu Fu +4
Recent research has shown that pruning large-scale language models for inference is an effective approach to improving model efficiency, significantly reducing model weights with m…
Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack
Yu Fu, Yufei Li, Wen Xiao +2
Recent developments in balancing the usefulness and safety of Large Language Models (LLMs) have raised a critical question: Are mainstream NLP tasks adequately aligned with safety…
Cross-Task Defense: Instruction-Tuning LLMs for Content Safety
Yu Fu, Wen Xiao, Jia Chen +4
Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization a…