具象化研究逻辑：面向定量句法的AI辅助工作流构建与增量优化
Reifying Research Logic: AI-Assisted Workflow Construction and Incremental Refinement for Quantitative Syntax
浏览论文内容
中文总结 AI 辅助
针对定量句法研究的步骤逻辑隐藏问题，提出QLWF可视化工作流平台，可通过AI辅助将自然语言描述转为可执行工作流，在基准测试中表现优异并发布相关可复用资源。
中文摘要 AI 辅助
定量语言研究通常依赖冗长的计算步骤链，但连接这些步骤的逻辑往往隐藏在脚本中，这使得分析的检查、共享和修订变得更为困难。针对定量句法领域，我们提出QLWF（定量语言工作流平台），这是一个可视化工作流平台，通过AI辅助的五阶段流水线将自然语言研究描述转化为可执行工作流。在此设置中，具象化将研究逻辑以工作流形式呈现，而形式化则为该工作流赋予确定性执行语义。语言模型仅在构建阶段使用，执行由固定节点库和引擎处理，这确保了生成的工作流可复现。QLWF还支持增量优化，因此保存的工作流可仅修改需要调整的部分，而非从头重建。为评估该方法，我们从定量句法文献中构建了包含64个任务的基准QL-Bench。在三轮运行中，QLWF为所有任务生成了结构有效且可执行的工作流，达到了98.4%的平均输出合理性，远高于基于提示的基线。在单独的包含12个任务的生命周期基准上，该优化过程在所有案例中均成功，且使用的令牌量约为完全重新生成所需的三分之一。本文还将节点库、基准、工作流模板和平台作为定量句法研究的可复用资源发布。
英文摘要
Quantitative language research often depends on long chains of computational steps, yet the logic connecting those steps usually remains buried in scripts. This makes analyses harder to inspect, share, and revise than they need to be. Focusing on quantitative syntax, we present QLWF, a visual workflow platform that turns natural-language research descriptions into executable workflows through an AI assisted five-stage pipeline. In this setting, reification makes the research logic visible as a workflow, while formalization gives that workflow deterministic execution semantics. The language model is used only during construction. Execution is handled by a fixed node library and engine, which keeps the resulting workflows reproducible. QLWF also supports incremental refinement, so saved workflows can be revised by changing only the parts that need to change rather than being rebuilt from scratch. To evaluate the approach, we build a 64-task benchmark called QL-Bench from the quantitative-syntax literature. Across three runs, QLWF produces structurally valid and executable workflows for every task and reaches a mean output-plausibility rate of 98.4%, well above the prompt-based baselines. On a separate 12-task lifecycle benchmark, this refinement process succeeds in every case and uses roughly one-third of the tokens required by full regeneration. The paper also releases the node library, benchmark, workflow templates, and platform as reusable resources for quantitative-syntax research.
