activity
20232026
collaborators

10 papers

cs.AI2026

When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutability

Steven Wang, Kyle Hunt, Shaojie Tang +1

LLM-based digital twins promise to reduce repeated human data collection by generating person- specific responses, yet existing evaluations provide little evidence about whether th…

cs.CL2025

Can Finetuing LLMs on Small Human Samples Increase Heterogeneity, Alignment, and Belief-Action Coherence?

Steven Wang, Kyle Hunt, Shaojie Tang +1

There is ongoing debate about whether large language models (LLMs) can serve as substitutes for human participants in survey and experimental research. While recent work in fields…

cs.LG2025

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation

Wenkai Guo, Xuefeng Liu, Haolin Wang +3

Fine-tuning large language models (LLMs) with local data is a widely adopted approach for organizations seeking to adapt LLMs to their specific domains. Given the shared characteri…

cs.CL2024

The Power of Adaptation: Boosting In-Context Learning through Adaptive Prompting

Shuzhang Cai, Twumasi Mensah-Boateng, Xander Kuksov +2

Large Language Models (LLMs) have demonstrated exceptional abilities across a broad range of language-related tasks, including generating solutions to complex reasoning problems. A…

cs.LG2024

Learning Submodular Sequencing from Samples

Jing Yuan, Shaojie Tang

This paper addresses the problem of sequential submodular maximization: selecting and ranking items in a sequence to optimize some composite submodular function. In contrast to mos…

cs.LG2024

The Power of Second Chance: Personalized Submodular Maximization with Two Candidates

Jing Yuan, Shaojie Tang

Most of existing studies on submodular maximization focus on selecting a subset of items that maximizes a \emph{single} submodular function. However, in many real-world scenarios,…