9 papers · 1 filter
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment
Tung-Ling Li, Hongliang Liu, Yuhao Wu
Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE tokenization f…
Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs
Hongliang Liu, Tung-Ling Li, Yuhao Wu
Perturbation probing generates task-specific causal hypotheses for FFN neurons in large language models using two forward passes per prompt and no backpropagation, followed by a on…
AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought
Weihua Zheng, Xin Huang, Zhengyuan Liu +7
Large language models (LLMs) have shown impressive multilingual capabilities through pretraining on diverse corpora. Although these models show strong reasoning abilities, their pe…
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
Yuhao Wu, Yushi Bai, Zhiqiang Hu +2
Ultra-long generation by large language models (LLMs) is a widely demanded scenario, yet it remains a significant challenge due to their maximum generation length limit and overall…
Lost in Stories: Consistency Bugs in Long Story Generation by LLMs
Junjie Li, Xinrui Guo, Yuhao Wu +3
What happens when a storyteller forgets its own story? Large Language Models (LLMs) can now generate narratives spanning tens of thousands of words, but they often fail to maintain…
SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models
Yuhao Wu, Yushi Bai, Zhiqiang Hu +2
Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text…