Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?

Conversational Tabular Data Analysis, a collaboration between humans and machines, enables real-time data exploration for informed decisionmaking. The challenges and costs of collecting realistic conversational logs for tabular data analysis hinder comprehensive quantitative evaluation of Large Language Models (LLMs) in this task. To mitigate this issue, we introduce COTA, a new benchmark to evaluate LLMs on conversational data analysis. COTA contains 1013 conversations, covering 4 practical scenarios: NORMAL, ACTION, PRIVATE, and PRIVATE ACTION. Notably, COTA is constructed by a multi-agent environment, DECISION COMPANY. This environment ensures efficiency and scalability of generating new conversational data. Our comprehensive study, conducted by data analysis experts, demonstrates that DECISION COMPANY is capable of producing diverse and high-quality data, laying the groundwork for efficient data annotation. We evaluate popular and advanced LLMs in COTA, which highlights the challenges of conversational tabular data analysis. Furthermore, we propose Adaptive Conversation Reflection (ACR), a selfgenerated reflection strategy that guides LLMs to learn from successful histories. Experiments demonstrate that ACR can evolve LLMs into effective conversational tabular data analysis agents, achieving a relative performance improvement of up to 35.14%. Code can be found at https: //tapilot-crossing.github.io/