用自然语言生成可交互的假设分析界面，提升准确性与可靠性。
Bridging Natural Language and Interactive What-If Interfaces via LLM-Generated Declarative Specification
- 将自然语言问题转为中间形式规范，再编译成可视化交互界面。
- 52.42% 的规范自动生成正确，修复后成功率升至80.42%。
- 适合需要精准假设分析的科研与商业用户，避免误导性结果。
假设分析（WIA）是用户通过调整参数、施加约束和数据筛选，在交互界面中探索和比较假设情景的迭代过程。现有工具难以有效支持：电子表格和商业智能工具设置繁琐，基于大模型的聊天界面语义脆弱，常误解意图且结果不一致。为此，我们提出两阶段流程：首先，大模型从自然语言问题生成普拉克萨规范语言（PSL）规范，捕捉分析意图与逻辑，支持验证与修复；其次，将规范编译为带参数控件和联动可视化的交互界面。我们在405个涵盖11种WIA类型、5个数据集和3个先进大模型的问题上进行评测。结果显示，各模型中52.42%的规范无需干预即可正确生成。通过分析失败案例，构建包含非功能性错误（无法编译）和功能性错误（编译通过但意图偏差）的错误分类体系。基于此，使用少量示例提示对故障项进行针对性修复，成功率达80.42%。最后，我们揭示未检测到的功能性错误会传播至界面，生成看似合理但误导性的可视化，证明中间规范在大模型驱动的WIA系统中对可靠连接自然语言与交互界面至关重要。
原文摘要 · Abstract (English)
What-if analysis (WIA) is an iterative, multi-step process where users explore and compare hypothetical scenarios by adjusting parameters, applying constraints, and scoping data through interactive interfaces. Current tools fall short of supporting effective interactive WIA: spreadsheet and BI tools require time-consuming and laborious setup, while LLM-based chatbot interfaces are semantically fragile, frequently misinterpret intent, and produce inconsistent results as conversations progress. To address these limitations, we present a two-stage workflow that translates natural language (NL) WIA questions into interactive visual interfaces via an intermediate representation, powered by the Praxa Specification Language (PSL): first, LLMs generate PSL specifications from NL questions capturing analytical intent and logic, enabling validation and repair of erroneous specifications; and second, the specifications are compiled into interactive visual interfaces with parameter controls and linked visualizations. We benchmark this workflow with 405 WIA questions spanning 11 WIA types, 5 datasets, and 3 state-of-the-art LLMs. The results show that across models, half of specifications (52.42%) are generated correctly without intervention. We perform an analysis of the failure cases and derive an error taxonomy spanning non-functional errors (specifications fail to compile) and functional errors (specifications compile but misrepresent intent). Based on the taxonomy, we apply targeted repairs on the failure cases using few-shot prompts and improve the success rate to 80.42%. Finally, we show how undetected functional errors propagate through compilation into plausible but misleading interfaces, demonstrating that the intermediate specification is critical for reliably bridging NL and interactive WIA interface in LLM-powered WIA systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。