11 papers
Representation-guided in-context learning for medical image interpretation with multimodal large language models
Minda Zhao, Fangyu Hu, Yan Luo +8
Medical image interpretation is central to diagnosis and care, yet adapting general-purpose multimodal large language models (MLLMs) often requires resource-intensive domain-specif…
Benign Nonconvex Landscape for Policy Optimization: Infinite-Horizon Discounted MDPs with General State and Action Spaces
Xin Chen, Minda Zhao
We study the optimization landscape for infinite-horizon discounted Markov decision processes (MDPs) with general state and action spaces under structured stationary policy classes…
Rare Diseases, Common Dilemmas: LLMs Prioritize Equal Resource Distribution over Patient Benefit in Decision-Making
Minda Zhao, Xu Han, Rishabh Goel +6
Clinical decision-making often involves prioritizing ethical values, such as beneficence, non-maleficence, respecting a patient's autonomy, and justice. Recent work has begun to as…
A Simple Solution to Improving Human Supervision of Algorithms: Evidence from Smart Vending
Minda Zhao, Brian Rongqing Han, Xin Chen +1
Organizations increasingly deploy autonomous artificial intelligence (AI) systems for operational decisions, such as inventory replenishment. Yet granting full override discretion…
Individual and Combined Effects of English as a Second Language and Typos on LLM Performance
Serena Liu, Yutong Yang, Prisha Sheth +9
Large language models (LLMs) are used globally, and because much of their training data is in English, they typically perform best on English inputs. As a result, many non-native E…
Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models
Minda Zhao, Yutong Yang, Chufei Peng +5
Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear. Here, we examine how first-person emotional framing i…
TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
Sung-Hoon Yoon, Ruizhi Qian, Minda Zhao +2
Large Language Models (LLMs) have become integral to many domains, making their safety a critical priority. Prior jailbreaking research has explored diverse approaches, including p…
Grading Scale Impact on LLM-as-a-Judge: Human-LLM Alignment Is Highest on 0-5 Grading Scale
Weiyue Li, Minda Zhao, Weixuan Dong +12
Large language models (LLMs) are increasingly used as automated evaluators, yet prior works demonstrate that these LLM judges often lack consistency in scoring when the prompt is a…
Large Language Models Are Bad Dice Players: LLMs Struggle to Generate Random Numbers from Statistical Distributions
Minda Zhao, Yilun Du, Mengyu Wang
As large language models (LLMs) transition from chat interfaces to integral components of stochastic pipelines and systems approaching general intelligence, the ability to faithful…
Hidden Convexity in Queueing Models
Xin Chen, Linwei Xin, Minda Zhao
We study the joint control of arrival and service rates in queueing systems with the objective of minimizing long-run expected cost minus revenue. Although the objective function i…
Breaking the Cold-Start Barrier: Reinforcement Learning with Double and Dueling DQNs
Minda Zhao
Recommender systems struggle to provide accurate suggestions to new users with limited interaction history, a challenge known as the cold-user problem. This paper proposes a reinfo…