← Search

Meiyun Wang

2 accepted papers

2025

Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge

NAACL 2025findings

Large language models (LLMs) have demonstrated impressive capabilities in handling long contexts, but challenges remain in capturing relational knowledge spread far apart within text. Connecting long-distance knowledge is important for solving tasks as the context length increases: imagine reading a…

2024

LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Prediction

ACL 2024findings

Recently, Large Language Models (LLMs) have attracted significant attention for their exceptional performance across a broad range of tasks, particularly in text analysis. However, the finance sector presents a distinct challenge due to its dependence on time-series data for complex forecasting task…

Cited by 17SourcePDFScholar