117 citations · 133 across the 24 of their papers we have counts for
8 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…
GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI
Zhesheng Zhang, Jiahao Lu, Wei Liu +8
In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual cont…
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…
On the Hidden Costs of Counterfactual Knowledge Training in LLM Unlearning
Xiaotian Ye, Xiaohan Wang, Mengqi Zhang +1
Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models to generate alternative fictitious knowledge in place o…
Uncovering Entity Identity Confusion in Multimodal Knowledge Editing
Shu Wu, Xiaotian Ye, Xinyu Mou +3
Multimodal knowledge editing (MKE) aims to correct the internal knowledge of large vision-language models after deployment, yet the behavioral patterns of post-edit models remain u…
Uncovering Context Reliance in Unstructured Knowledge Editing
Zisheng Zhou, Mengqi Zhang, Shiguang Wu +4
Editing Large language models (LLMs) with real-world, unstructured knowledge is essential for correcting and updating their internal parametric knowledge. In this work, we revisit…
Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering
Fangan Dong, Zuming Yan, Xuri Ge +7
Despite the strong reasoning capabilities of recent large language models (LLMs), achieving reliable performance on challenging tasks often requires post-training or computationall…
Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapse
Chi Zhang, Mengqi Zhang, Xiaotian Ye +5
Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing appr…