5 papers · 1 filter
Generalizable Model Editing Could Be More Than Direct Generalization
Xiaotian Ye, Chunyao Yang, Xiaohan Wang +4
A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating and evaluating LLM behavior…
CRANE: Knowledge Editing for Reasoning MLLMs
Han Huang, Hao Wang, Mengqi Zhang +3
The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers, has introduced a new challen…
From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation
Liuji Chen, Zeyu Zhang, Xinyuan Zhang +4
Personalized text generation requires models to capture user-specific writing styles from historical data. Existing approaches based on retrieval, parameter-efficient fine-tuning,…
Reading the Cell, Designing the Cure: Perturbation-Conditioned Molecular Diffusion for Function-Oriented Drug Design
Ziyu Xu, Zijian Zhang, Liang Wang +3
When reliable target structures are unavailable at scale or phenotypes arise from dysregulated pathways, transcriptomic perturbations provide a system-level functional readout for…
CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation
Zhao Tong, Chunlin Gong, Yiping Zhang +5
From generating headlines to fabricating news, the Large Language Models (LLMs) are typically assessed by their final outputs, under the safety assumption that a refusal response s…