OmniStruct: Universal Text-to-Structure Generation across Diverse Schemas
By: James Y. Huang , Wenxuan Zhou , Nan Xu and more
Potential Business Impact:
Teaches small computers to make organized answers.
The ability of Large Language Models (LLMs) to generate structured outputs that follow arbitrary schemas is crucial to a wide range of downstream tasks that require diverse structured representations of results such as information extraction, table generation, and function calling. While modern LLMs excel in generating unstructured responses in natural language, whether this advancement translates to a strong performance on text-to-structure tasks remains unclear. To bridge this gap, we first introduce OmniStruct, a comprehensive benchmark for assessing LLMs' capabilities on diverse text-to-structure tasks such as information extraction, table generation, and function calling. We build OmniStruct by identifying existing datasets across a wide range of tasks that are suitable for a structured answer format, and adapting them under a unified text-to-structure problem setting. To facilitate the development of efficient text-to-structure models, we collect high-quality training data via synthetic task generation. Without using any supervised data for OmniStruct tasks, our experiments demonstrate the possibility of fine-tuning much smaller models on synthetic data into universal structured generation models that can rival the performance of GPT-4o.
Similar Papers
Automata-Based Steering of Large Language Models for Diverse Structured Generation
Computation and Language
Creates more varied computer-generated text.
The Effectiveness of Large Language Models in Transforming Unstructured Text to Standardized Formats
Artificial Intelligence
Turns messy text into organized lists.
LLM driven Text-to-Table Generation through Sub-Tasks Guidance and Iterative Refinement
Computation and Language
Helps computers turn messy notes into organized charts.