AutoDSL: Automated domain-specific language design for structural representation of procedures with constraints
Yu-Zhe Shi, Haofei Hou, Zhangqian Bi, Fanxu Meng, Xiang Wei, Lecheng Ruan, Qining Wang
摘要
Accurate representation of procedures in restricted scenarios, such as non-standardized scientific experiments, requires precise depiction of constraints. Unfortunately, Domainspecific Language (DSL), as an effective tool to express constraints structurally, often requires case-by-case hand-crafting, necessitating customized, labor-intensive efforts. To overcome this challenge, we introduce the AutoDSL framework to automate DSL-based constraint design across various domains. Utilizing domain specified experimental protocol corpora, AutoDSL optimizes syntactic constraints and abstracts semantic constraints. Quantitative and qualitative analyses of the DSLs designed by AutoDSL across five distinct domains highlight its potential as an auxiliary module for language models, aiming to improve procedural planning and execution.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper8
- Weak-to-Strong Prompts with Lightweight-to-Powerful LLMs for High-Accuracy, Low-Cost, and Explainable Data TransformationChanglun Li, Chenyu Yang, Yuyu Luo, Ju Fan 等VLDB 2025 · 被引用 6 次
- Expert-level protocol translation for self-driving labsYu-Zhe Shi, Fanxu Meng, Haofei Hou, Zhangqian Bi 等NeurIPS 2024 · 被引用 6 次
- Hierarchically Encapsulated Representation for Protocol Design in Self-Driving LabsYu-Zhe Shi, Mingchen Liu, Fanxu Meng, Qiao Xu 等ICLR 2025
- Targeted control of fast prototyping through domain-specific interfaceYu-Zhe Shi, Mingchen Liu, Hanlu Ma, Qiao Xu 等ICML 2025
- Text-to-ES Bench: A Comprehensive Benchmark for Converting Natural Language to Elasticsearch QueryDongge Xue, Zhili Pu, Zhentao Xia, Hongli Sun 等ACL 2025
它引用的顶会 Paper7
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah 等NeurIPS 2020 · 被引用 64,255 次
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied AgentsWenlong Huang, Pieter Abbeel, Deepak Pathak, Igor MordatchICML 2022 · 被引用 1,539 次
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsLei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu 等ACL 2023 · 被引用 249 次
- Scallop: From Probabilistic Deductive Databases to Scalable Differentiable ReasoningJiani Huang, Ziyang Li, Binghong Chen, Karan Samel 等NeurIPS 2021 · 被引用 101 次
相关 Paper
- DocCGen: Document-based Controlled Code GenerationSameer Pimparkhede, Mehant Kammakomati, Srikanth Tamilselvam, Prince Kumar 等EMNLP 2024 · 被引用 4 次
- BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in BiologyOdhran O'Donoghue, Aleksandar Shtedritski, John Ginger, Ralph Abboud 等EMNLP 2023 · 被引用 13 次
- Distilling Script Knowledge from Large Language Models for Constrained Language PlanningSiyu Yuan, Jiangjie Chen, Ziquan Fu, Xuyang Ge 等ACL 2023 · 被引用 14 次
- Tool Learning in the Wild: Empowering Language Models as Automatic Tool AgentsZhengliang Shi, Shen Gao, Lingyong Yan, Yue Feng 等WWW 2025 · 被引用 59 次
- Unleashing Scientific Reasoning for Bio-experimental Protocol Generation via Structured Component-based Reward MechanismHaoran Sun, Yankai Jiang, Zhenyu Tang, Yaning Pan 等ICLR 2026 · 被引用 2 次
