6 papers
Bias as a Virtue: Rethinking Generalization under Distribution Shifts
Ruixuan Chen, Wentao Li, Jiahui Xiao +3
Machine learning models often degrade when deployed on data distributions different from their training data. Challenging conventional validation paradigms, we demonstrate that hig…
StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization
Yiming Tang, Yi Fan, Chenxiao Yu +3
The integration of large language models (LLMs) into information retrieval systems introduces new attack surfaces, particularly for adversarial ranking manipulations. We present $\…
Enhancing Long Context Performance in LLMs Through Inner Loop Query Mechanism
Yimin Tang, Yurong Xu, Ning Yan +1
Transformers have a quadratic scaling of computational complexity with input size, which limits the input context window size of large language models (LLMs) in both training and i…
Demonstration Notebook: Finding the Most Suited In-Context Learning Example from Interactions
Yiming Tang, Bin Dong
Large language models (LLMs) benefit greatly from prompt engineering, with in-context learning standing as a pivital technique. While former approaches have provided various ways t…
Prompt Engineering Through the Lens of Optimal Control
Yifan Luo, Yiming Tang, Chengfeng Shen +2
Prompt Engineering (PE) has emerged as a critical technique for guiding Large Language Models (LLMs) in solving intricate tasks. Its importance is highlighted by its potential to s…
A Minesweeper Solver Using Logic Inference, CSP and Sampling
Yimin Tang, Tian Jiang, Yanpeng Hu
Minesweeper as a puzzle video game and is proved that it is an NPC problem. We use CSP, Logic Inference and Sampling to make a minesweeper solver and we limit us each select in 5 s…