8 papers
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…
CogniDir: Combating Cognitive Malicious Comments via Adaptive Distributional Learning for Robust Fake News Detection
Zhao Tong, Chunlin Gong, Yimeng Gu +5
The proliferation of Large Language Models (LLMs) has enabled a new class of psychologically grounded malicious comments, shifting fake news attacks from surface-level textual nois…
REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editing
Haitian Zhong, Yuhuan Liu, Ziyang Xu +6
Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even w…
Uncovering Overfitting in Large Language Model Editing
Mengqi Zhang, Xiaotian Ye, Qiang Liu +3
Knowledge editing has been proposed as an effective method for updating and correcting the internal knowledge of Large Language Models (LLMs). However, existing editing methods oft…