paper-with-me

Papers

Mining Documentation to Extract Hyperparameter Schemas

2020-06-30 · Guillaume Baudart, Peter D. Kirchner, Martin Hirzel, Kiran Kate

AI automation tools need machine-readable hyperparameter schemas to define their search spaces. At the same time, AI libraries often come with good human-readable documentation. While such documentation contains most of the necessary information, it is unfortunately not ready to consume by tools. This paper describes how to automatically mine Python docstrings in AI libraries to extract JSON Schemas for their hyperparameters. We evaluate our approach on 119 transformers and estimators from three different libraries and find that it is effective at extracting machine-readable schemas. Our vision is to reduce the burden to manually create and maintain such schemas for AI automation tools and broaden the reach of automation to larger libraries and richer schemas.

📄 PDF Abstract BibTeX arXiv:2006.16984

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

RAG Strategies for Natural Language-Based SQL Query and REST API Call Generation

2026-02-06 · Michael Marketsmüller, Simon Martin, Tim Schlippe arxiv

Enterprise software systems commonly expose business functionality through both relational databases and REST APIs. Accessing these interfaces requires specialized technical knowledge, as users must determine whether a r…

Code Generation

Contract2Tool: Learning Preconditions and Effects for Reliable Tool-Augmented LLM Agents

2026-06-05 · Rahul Suresh Babu, Laxmipriya Ganesh Iyer arxiv

Tool-augmented large language model agents increasingly rely on external APIs, but standard tool schemas describe how to call a tool, not when the tool is causally appropriate or what task state it produces. Causal tool …

LongDA: Benchmarking LLM Agents for Long-Document Data Analysis

2026-01-05 · Yiyang Li, Zheyuan Zhang, Tianyi Ma, Zehong Wang 외 arxiv

We introduce LongDA, a data analysis benchmark for evaluating LLM-based agents under documentation-intensive analytical workflows. In contrast to existing benchmarks that assume well-specified schemas and inputs, LongDA …

SciSchema.org: A Multidisciplinary Collection of Schemas for Structured Scientific Process Descriptions

2026-07-30 · Jennifer D'Souza, Sameer Sadruddin, Anisa Rula, Ana Bossler 외 arxiv

Scientific processes are often described in heterogeneous article discourse, with details needed for comparison, reproducibility, reuse, and automation dispersed across prose, tables, figures, protocols, and supplementar…

Information ExtractionKnowledge Graphs

LLMs4SchemaDiscovery: A Human-in-the-Loop Workflow for Scientific Schema Mining with Large Language Models

2025-04-01 · Sameer Sadruddin, Jennifer D'Souza, Eleni Poupaki, Alex Watkins 외

Extracting structured information from unstructured text is crucial for modeling real-world processes, but traditional schema mining relies on semi-structured data, limiting scalability. This paper introduces schema-mine…