14 papers
EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and Reuse
Dongsheng Shi, Yue Li, Xin Yi +1
Large language model (LLM) driven multi-agent systems have shown promise in complex clinical reasoning, yet existing approaches rely on static strategies and lack persistent clinic…
Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks
Shunfan Zheng, Dongsheng Shi, Yue Li +3
Large Language Models (LLMs) are transforming database interaction paradigms, evolving from simple query translators to autonomous database administrators (DBAs). However, current…
Construction-Driven Injection: Linguistically-Grounded Edit-Based Code-Mixing Fingerprints for Large Language Models
Yongyi Cui, Yue Li, Tianbao Jiang +1
Large language models (LLMs) are costly intellectual assets that remain exposed to unauthorized redistribution and commercial misuse. Injected fingerprints, i.e., trigger--target p…
SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative Workflow
Dongsheng Shi, Yue Li, Xin Yi +3
The intricate nature of modern surgical care necessitates intelligent systems that can synthesize extensive patient records, support collaborative decision-making, and provide tran…
Pooling Engram Conditional Memory in Large Language Models using CXL
Ruiyang Ma, Teng Ma, Zhiyuan Su +11
Engram conditional memory has emerged as a promising component for LLMs by decoupling static knowledge lookup from dynamic computation. Since Engram exhibits sparse access patterns…
AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models
Yue Li, Xin Yi, Dongsheng Shi +3
Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs). However, vision-agnostic water…
Unified Defense for Large Language Models against Jailbreak and Fine-Tuning Attacks in Education
Xin Yi, Yue Li, Dongsheng Shi +3
Large Language Models (LLMs) are increasingly integrated into educational applications. However, they remain vulnerable to jailbreak and fine-tuning attacks, which can compromise s…
From Construction to Injection: Edit-Based Fingerprints for Large Language Models
Yue Li, Xin Yi, Dongsheng Shi +3
Reliable model fingerprints are essential for protecting large language models (LLMs) against unauthorized redistribution and commercial misuse. In black-box deployment, verificati…
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
Yue Li, Xin Yi, Dongsheng Shi +3
With the increasing size of Large Vision-Language Models (LVLMs), network pruning techniques aimed at compressing models for deployment in resource-constrained environments have ga…
Unified attacks to large language model watermarks: spoofing and scrubbing in unauthorized knowledge distillation
Xin Yi, Yue Li, Shunfan Zheng +3
Watermarking has emerged as a critical technique for combating misinformation and protecting intellectual property in large language models (LLMs). A recent discovery, termed water…
Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks
Xin Yi, Yue Li, Dongsheng Shi +3
Ensuring safety alignment is a critical requirement for large language models (LLMs), particularly given increasing deployment in real-world applications. Despite considerable adva…
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning
Xin Yi, Shunfan Zheng, Linlin Wang +3
The emergence of finetuning-as-a-service has revealed a new vulnerability in large language models (LLMs). A mere handful of malicious data uploaded by users can subtly manipulate…
A safety realignment framework via subspace-oriented model fusion for large language models
Xin Yi, Shunfan Zheng, Linlin Wang +2
The current safeguard mechanisms for large language models (LLMs) are indeed susceptible to jailbreak attacks, making them inherently fragile. Even the process of fine-tuning on ap…
Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models
Xin Yi, Linlin Wang, Xiaoling Wang +1
Impressive results have been achieved in natural language processing (NLP) tasks through the training of large language models (LLMs). However, these models occasionally produce to…