2 citations · 3 across the 8 of their papers we have counts for
9 papers
Value of Information: A Framework for Human-Agent Communication
Yijiang River Dong, Tiancheng Hu, Zheng Hui +4
Large Language Model (LLM) agents deployed for real-world tasks face a fundamental dilemma: user requests are underspecified, yet agents must decide whether to act on incomplete in…
Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding
Yijiang River Dong, Tiancheng Hu, Zheng Hui +1
Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting in…
Confidence Estimation for LLMs in Multi-turn Interactions
Caiqi Zhang, Ruihan Yang, Xiaochen Zhu +5
While confidence estimation is a promising direction for mitigating hallucinations in Large Language Models (LLMs), current research overwhelmingly focuses on single-turn settings.…
Digital Engagement, Income Disparities, and Job Seeking in the United States since 2010
Shaolong Wu, Yijiang River Dong, Siming He
Surveys often record how frequently people use the internet without measuring the infrastructures, skills, and support systems that make digital participation possible. Using the U…
Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning
Zheng Hui, Yijiang River Dong, Sanhanat Sivapiromrat +2
When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM…
TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law
Zheng Hui, Yijiang River Dong, Ehsan Shareghi +1
As large language models (LLMs) are increasingly deployed in high-risk domains such as law, finance, and medicine, systematically evaluating their domain-specific safety and compli…
When Personalization Meets Reality: A Multi-Faceted Analysis of Personalized Preference Learning
Yijiang River Dong, Tiancheng Hu, Yinhong Liu +2
While Reinforcement Learning from Human Feedback (RLHF) is widely used to align Large Language Models (LLMs) with human preferences, it typically assumes homogeneous preferences ac…
Can LLM be a Personalized Judge?
Yijiang River Dong, Tiancheng Hu, Nigel Collier
Ensuring that large language models (LLMs) reflect diverse user values and preferences is crucial as their user bases expand globally. It is therefore encouraging to see the growin…
UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
Yijiang River Dong, Hongzhou Lin, Mikhail Belkin +2
Mitigating the retention of sensitive or private information in large language models is essential for enhancing privacy and safety. Existing unlearning methods, like Gradient Asce…