activity
20232026
most citedSurvey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks

37 citations · 37 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

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…

cs.CL2026

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…

cs.CL2026

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…

cs.CL2024

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…

cs.CL2024

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…

cs.CL2023

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…