Current evaluations of multimodal unlearning typically focus on whether a model stops outputting target information. This surface-level criterion, however, masks two critical failure modes. First, knowledge suppression techniques often induce confabulation, leading the model to hallucinate facts about the unlearned sub...
Hao-Dong Chen, Sheng-Tao Wen, Dong Liang et al.· 0 citations
This work introduces two lightweight execution-consistent interfaces, Future-Sequence for TD-MPC2 and Applied-Action Feedback for DreamerV3, that correct future-action timeline mismatch between imagined and executed action sequences without modifying the pretrained world models.
Sheng-Tao Wen, Xiang Chen, Yu Tian et al.· 0 citations
SPARK is proposed, a retention-correction decomposition that first freezes the learned post-task distribution and then applies selective correction around this stable reference and achieves effective selective PII suppression while preserving strong continual-learning utility and knowledge retention across diverse sett...
VARM-Bench provides an auditable and reproducible benchmark for evaluating verifiable moderation rationales in Chinese abusive-speech moderation, and shows that strong label-level performance can conceal substantial errors in complete moderation records.
Mingyu Yuan, Sheng-Tao Wen, Ling-Bing Guo et al.· 0 citations
OaK is presented, an ontology-as-a-kernel framework that dynamically constructs and refines task-oriented ontologies for LLM agents and shows that OaK improves standard LLM agents, strengthens evidence grounding, and boosts the reliability of multi-step reasoning.
Xiaohui Zhang, Ze-Qun Sun, Cheng Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.