60 citations · 80 across the 13 of their papers we have counts for
15 papers
AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents
Tianzhuo Yang, Zirui Mi, Yantao Huang +4
Safety alignment for large language models (LLMs) in conversational settings is largely framed around whether to answer or refuse a request. In agentic settings, however, the same…
Learning behavior accounts for background-related advantage in AI-assisted education
Jingwei Yi, Yueqi Xie, Jiyan He +7
Generative AI has been found, and will likely be found increasingly, useful in education. However, existing AI-for-education studies provide inconsistent evidence on its average ef…
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
Guoxi Zhang, Jiawei Chen, Tianzhuo Yang +4
As Large Language Models (LLMs) expand in capability and application scope, their trustworthiness becomes critical. A vital risk is intrinsic deception, wherein models strategicall…
ImageRef-VL: Enabling Contextual Image Referencing in Vision-Language Models
Jingwei Yi, Junhao Yin, Ju Xu +4
Vision-Language Models (VLMs) have demonstrated remarkable capabilities in understanding multimodal inputs and have been widely integrated into Retrieval-Augmented Generation (RAG)…
Elephant in the Room: Unveiling the Impact of Reward Model Quality in Alignment
Yan Liu, Xiaoyuan Yi, Xiaokang Chen +6
The demand for regulating potentially risky behaviors of large language models (LLMs) has ignited research on alignment methods. Since LLM alignment heavily relies on reward models…
Measuring Human Contribution in AI-Assisted Content Generation
Yueqi Xie, Tao Qi, Jingwei Yi +7
With the growing prevalence of generative artificial intelligence (AI), an increasing amount of content is no longer exclusively generated by humans but by generative AI models wit…
Controlling risks of AI in chemical science with agents
Jiyan He, Weitao Feng, Haoxiang Guan +11
Artificial intelligence is rapidly advancing scientific discovery, but this progress carries risks of misuse, such as the creation of harmful substances, or circumvention of establ…
Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models
Jingwei Yi, Yueqi Xie, Bin Zhu +4
The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection a…
Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark
Wenjun Peng, Jingwei Yi, Fangzhao Wu +7
Large language models (LLMs) have demonstrated powerful capabilities in both text understanding and generation. Companies have begun to offer Embedding as a Service (EaaS) based on…
Effective and Efficient Query-aware Snippet Extraction for Web Search
Jingwei Yi, Fangzhao Wu, Chuhan Wu +4
Query-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. Although important, it…
Robust Quantity-Aware Aggregation for Federated Learning
Jingwei Yi, Fangzhao Wu, Huishuai Zhang +4
Federated learning (FL) enables multiple clients to collaboratively train models without sharing their local data, and becomes an important privacy-preserving machine learning fram…
UA-FedRec: Untargeted Attack on Federated News Recommendation
Jingwei Yi, Fangzhao Wu, Bin Zhu +4
News recommendation is critical for personalized news distribution. Federated news recommendation enables collaborative model learning from many clients without sharing their raw d…
Tiny-NewsRec: Effective and Efficient PLM-based News Recommendation
Yang Yu, Fangzhao Wu, Chuhan Wu +2
News recommendation is a widely adopted technique to provide personalized news feeds for the user. Recently, pre-trained language models (PLMs) have demonstrated the great capabili…
Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News Recommendation
Jingwei Yi, Fangzhao Wu, Chuhan Wu +3
News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users' historical news click behavior data, w…
DebiasedRec: Bias-aware User Modeling and Click Prediction for Personalized News Recommendation
Jingwei Yi, Fangzhao Wu, Chuhan Wu +3
News recommendation is critical for personalized news access. Existing news recommendation methods usually infer users' personal interest based on their historical clicked news, an…