Jingwei Yi

• University of Science and Technology of China

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 for optimization or evaluation, neglecting the quality of reward models may cause unreliable results or even misalignment. Despite the vital role reward models play in a...

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 with human guidance. This shift presents notable challenges for the delineation of originality due to the varying degrees of human contribution in AI-assisted works. This st...

The integration of large language models (LLMs) with external content has enabled more up-to-date and wide-ranging applications of LLMs, such as Microsoft Copilot. However, this integration has also exposed LLMs to the risk of indirect prompt injection attacks, where an attacker can embed malicious instructions within external content, compromising...

ChatGPT is a societally impactful artificial intelligence tool with millions of users and integration into products such as Bing. However, the emergence of jailbreak attacks notably threatens its responsible and secure use. Jailbreak attacks use adversarial prompts to bypass ChatGPT’s ethics safeguards and engender harmful responses. This paper inv...

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 these LLMs, which can benefit various natural language processing (NLP) tasks for customers. However, previous studies have shown that EaaS is vulnerable to model extrac...

ChatGPT is a societally-impactful AI tool with millions of users and integration into products such as Bing. However, the emergence of Jailbreak Attacks, which can engender harmful responses by bypassing ChatGPT's ethics safeguards, significantly threatens its responsible and secure use. This paper investigates the severe, yet under-explored proble...

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 is very rarely studied. In this paper, we propose an effective query-aware webpage snippet extraction method named DeepQSE, aiming to select a few sentences which can be...

Federated learning (FL) enables multiple clients to collaboratively train models without sharing their local data, and becomes an important privacy-preserving machine learning framework. However, classical FL faces serious security and robustness problem, e.g., malicious clients can poison model updates and at the same time claim large quantities t...

News recommendation is critical for personalized news distribution. Federated news recommendation enables collaborative model learning from many clients without sharing their raw data. It is promising for privacy-preserving news recommendation. However, the security of federated news recommendation is still unclear. In this paper, we study this pro...

Personalized news recommendation has been widely adopted to improve user experience. Recently, pre-trained language models (PLMs) have demonstrated the great capability of natural language understanding and the potential of improving news modeling for news recommendation. However, existing PLMs are usually pre-trained on general corpus such as Book...

News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users' historical news click behavior data, which may lead to privacy concerns and hazards. Federated Learning is a privacy-preserving framework for multiple clients to collaboratively train models without sharing t...

News recommendation is critical for personalized news access. Existing news recommendation methods usually infer users' personal interest based on their historical clicked news, and train the news recommendation models by predicting future news clicks. A core assumption behind these methods is that news click behaviors can indicate user interest. H...