9 citations · 21 across the 16 of their papers we have counts for
17 papers
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
Kexin Chen, Yi Liu, Haonan Zhang +3
As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious safety concern. Existing deception monitors either score visible transcripts or…
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
Qinyan Zhou, Peixin Zhang, Jun Sun +2
While safety alignment and guardrails help large language models (LLMs) avoid harmful outputs, they can also induce overrefusal, i.e., unwarranted rejection of benign queries that…
FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models
Xinyuan An, Tao Luo, Gengyun Peng +3
Vision-Language-Action (VLA) models are emerging as a cornerstone for robotics, with flow-matching policies like showing great promise in generating smooth, continuous action…
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
Haonan Zhang, Dongxia Wang, Yi Liu +2
Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the mag…
RP-CATE: Recurrent Perceptron-based Channel Attention Transformer Encoder for Industrial Hybrid Modeling
Haoran Yang, Yinan Zhang, Wenjie Zhang +5
Nowadays, industrial hybrid modeling which integrates both mechanistic modeling and machine learning-based modeling techniques has attracted increasing interest from scholars due t…
When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI
Yanhui Li, Qi Zhou, Zhihong Xu +3
Large vision-language models (LVLMs) are increasingly used for tasks where detecting multimodal harmful content is crucial, such as online content moderation. However, real-world h…
ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal
Haonan Zhang, Dongxia Wang, Yi Liu +5
Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures - a critical functional flaw that u…
CrossPL: Evaluating Large Language Models on Cross Programming Language Code Generation
Zhanhang Xiong, Dongxia Wang, Yuekang Li +2
As large language models (LLMs) become increasingly embedded in software engineering workflows, a critical capability remains underexplored: generating correct code that enables cr…
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
Kexin Chen, Dongxia Wang, Yi Liu +2
Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repea…
LightKG: Efficient Knowledge-Aware Recommendations with Simplified GNN Architecture
Yanhui Li, Dongxia Wang, Zhu Sun +2
Recently, Graph Neural Networks (GNNs) have become the dominant approach for Knowledge Graph-aware Recommender Systems (KGRSs) due to their proven effectiveness. Building upon GNN-…
Enhancing New-item Fairness in Dynamic Recommender Systems
Huizhong Guo, Zhu Sun, Dongxia Wang +3
New-items play a crucial role in recommender systems (RSs) for delivering fresh and engaging user experiences. However, traditional methods struggle to effectively recommend new-it…
MRP-LLM: Multitask Reflective Large Language Models for Privacy-Preserving Next POI Recommendation
Ziqing Wu, Zhu Sun, Dongxia Wang +3
Large language models (LLMs) have shown promising potential for next Point-of-Interest (POI) recommendation. However, existing methods only perform direct zero-shot prompting, lead…
Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agents
Zihan Liu, Ruinan Zeng, Dongxia Wang +5
In industrial control systems, the generation and verification of Programmable Logic Controller (PLC) code are critical for ensuring operational efficiency and safety. While Large…
Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
Kexin Chen, Yi Liu, Dongxia Wang +2
Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be…
S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
Xiaohan Yuan, Jinfeng Li, Dongxia Wang +9
Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities. However, recent evidence indicates that…
KG4RecEval: Does Knowledge Graph Really Matter for Recommender Systems?
Haonan Zhang, Dongxia Wang, Zhu Sun +4
Recommender systems (RSs) are designed to provide personalized recommendations to users. Recently, knowledge graphs (KGs) have been widely introduced in RSs to improve recommendati…
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
Qi Zhou, Dongxia Wang, Tianlin Li +5
Guided image synthesis methods, like SDEdit based on the diffusion model, excel at creating realistic images from user inputs such as stroke paintings. However, existing efforts ma…