10 papers
Beyond Tokens: A Survey on Decoding Methods for Large Language and Vision-Language Models
Haoran Wang, Xiongxiao Xu, Philip S. Yu +1
Large language models (LLMs) and large vision-language models (LVLMs) have demonstrated impressive generative capabilities, yet ensuring their outputs align with user intent is sti…
Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning
Yuyang Luo, Haoran Wang, Kai Shu
Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks. However, manually authored skills often adapt poorly to long-horizon tas…
Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation
Haoran Wang, Xiongxiao Xu, Baixiang Huang +1
Retrieval-Augmented Generation (RAG) enhances the factual accuracy of large language models (LLMs) by conditioning outputs on external knowledge sources. However, when retrieval in…
On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective
Yue Huang, Chujie Gao, Siyuan Wu +63
Generative Foundation Models (GenFMs) have emerged as transformative tools. However, their widespread adoption raises critical concerns regarding trustworthiness across dimensions.…
Do LLMs Know What Is Private Internally? Probing and Steering Contextual Privacy Norms in Large Language Model Representations
Haoran Wang, Li Xiong, Kai Shu
Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private information in situations where…
Big2Small: A Unifying Neural Network Framework for Model Compression
Jing-Xiao Liao, Haoran Wang, Tao Li +4
With the development of foundational models, model compression has become a critical requirement. Various model compression approaches have been proposed such as low-rank decomposi…