Tag
This article introduces an open-source tool called TradingView MCP Bridge, which connects Claude Code with the locally running TradingView Desktop via the MCP protocol, enabling AI to read charts in real time, develop Pine Script strategies, perform historical backtesting, etc., forming a powerful trading charting combo.
This paper investigates methods for improving LLM accuracy in chart data extraction, finding that spatial priming via coordinate grids significantly outperforms semantic prompting strategies.
This paper introduces Misviz, a benchmark dataset of 2,604 real-world visualizations and 57,665 synthetic ones annotated with 12 types of misleading design violations, enabling automated detection of deceptive charts. The work evaluates state-of-the-art multimodal LLMs and rule-based systems on this challenging task, addressing the gap in resources for training AI models to combat data visualization misinformation.