10 papers
Statistical Impossibility and Possibility of Aligning LLMs with Human Preferences: From Condorcet Paradox to Nash Equilibrium
Kaizhao Liu, Qi Long, Zhekun Shi +2
Aligning large language models (LLMs) with diverse human preferences is critical for ensuring fairness and informed outcomes when deploying these models for decision-making. In thi…
Mitigating Privacy-Utility Trade-off in Decentralized Federated Learning via -Differential Privacy
Xiang Li, Buxin Su, Chendi Wang +2
Differentially private (DP) decentralized Federated Learning (FL) allows local users to collaborate without sharing their data with a central server. However, accurately quantifyin…
Robust Detection of Watermarks for Large Language Models Under Human Edits
Xiang Li, Feng Ruan, Huiyuan Wang +2
Watermarking has offered an effective approach to distinguishing text generated by large language models (LLMs) from human-written text. However, the pervasive presence of human ed…
A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules
Xiang Li, Feng Ruan, Huiyuan Wang +2
Since ChatGPT was introduced in November 2022, embedding (nearly) unnoticeable statistical signals into text generated by large language models (LLMs), also known as watermarking,…
On the Algorithmic Bias of Aligning Large Language Models with RLHF: Preference Collapse and Matching Regularization
Jiancong Xiao, Ziniu Li, Xingyu Xie +4
Accurately aligning large language models (LLMs) with human preferences is crucial for informing fair, economically sound, and statistically efficient decision-making processes. Ho…
Optimal Estimation of Watermark Proportions in Hybrid AI-Human Texts
Xiang Li, Garrett Wen, Weiqing He +3
Text watermarks in large language models (LLMs) are an increasingly important tool for detecting synthetic text and distinguishing human-written content from LLM-generated text. Wh…