4 papers
From Hypotheses to Factors: Constrained LLM Agents in Cryptocurrency Markets
Yikuan Huang, Zheqi Fan, Kaiqi Hu +1
LLM agents are promising tools for empirical discovery, but their flexibility can also turn discovery into uncontrolled search. We study how to use agents under a reproducible prot…
Cross-Stock Predictability via LLM-Augmented Semantic Networks
Yikuan Huang, Zheqi Fan, Kaiqi Hu +1
Text-based financial networks are increasingly used to study cross-stock return predictability. A common approach constructs links from similarities in firms' disclosure embeddings…
Do VLMs Truly "Read" Candlesticks? A Multi-Scale Benchmark for Visual Stock Price Forecasting
Kaiqi Hu, Linda Xiao, Shiyue Xu +2
Vision-language models(VLMs) are increasingly applied to visual stock price forecasting, yet existing benchmarks inadequately evaluate their understanding of stock price in candles…
Short-Path Prompting in LLMs: Analyzing Reasoning Instability and Solutions for Robust Performance
Zuoli Tang, Junjie Ou, Kaiqin Hu +6
Recent years have witnessed significant progress in large language models' (LLMs) reasoning, which is largely due to the chain-of-thought (CoT) approaches, allowing models to gener…