Generating Structured Outputs from Language Models: Benchmark and Studies

• URL: http://arxiv.org/abs/2501.10868v2
• Date: Mon, 10 Feb 2025 15:41:37 GMT
• Title: Generating Structured Outputs from Language Models: Benchmark and Studies
• Authors: Saibo Geng, Hudson Cooper, Michał Moskal, Samuel Jenkins, Julian Berman, Nathan Ranchin, Robert West, Eric Horvitz, Harsha Nori,
• Abstract summary: Constrained decoding has emerged as the dominant technology across sectors for enforcing structured outputs during generation.<n>We present an evaluation framework to assess constrained decoding approaches across three critical dimensions: efficiency in generating constraint-compliant outputs, coverage of diverse quality of the generated outputs.<n>Our work provides actionable insights for improving constrained decoding frameworks and setting a new standard for evaluating constrained decoding structured generation.
• Score: 24.017253364927086
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reliably generating structured outputs has become a critical capability for modern language model (LM) applications. Constrained decoding has emerged as the dominant technology across sectors for enforcing structured outputs during generation. Despite its growing adoption, little has been done with the systematic evaluation of the behaviors and performance of constrained decoding. Constrained decoding frameworks have standardized around JSON Schema as a structured data format, with most uses guaranteeing constraint compliance given a schema. However, there is poor understanding of the effectiveness of the methods in practice. We present an evaluation framework to assess constrained decoding approaches across three critical dimensions: efficiency in generating constraint-compliant outputs, coverage of diverse constraint types, and quality of the generated outputs. To facilitate this evaluation, we introduce JSONSchemaBench, a benchmark for constrained decoding comprising 10K real-world JSON schemas that encompass a wide range of constraints with varying complexity. We pair the benchmark with the existing official JSON Schema Test Suite and evaluate six state-of-the-art constrained decoding frameworks, including Guidance, Outlines, Llamacpp, XGrammar, OpenAI, and Gemini. Through extensive experiments, we gain insights into the capabilities and limitations of constrained decoding on structured generation with real-world JSON schemas. Our work provides actionable insights for improving constrained decoding frameworks and structured generation tasks, setting a new standard for evaluating constrained decoding and structured generation. We release JSONSchemaBench at https://github.com/guidance-ai/jsonschemabench

Related papers

• WritingBench: A Comprehensive Benchmark for Generative Writing [87.48445972563631]
  We present WritingBench, a benchmark designed to evaluate large language models (LLMs) across 6 core writing domains and 100, encompassing creative, persuasive, informative, and technical writing. We propose a query-dependent evaluation framework that empowers LLMs to dynamically generate instance-specific assessment criteria. This framework is complemented by a fine-tuned critic model for criteria-aware scoring, enabling evaluations in style, format and length.
  arXiv  Detail & Related papers  (2025-03-07T08:56:20Z)
• Learning to Generate Structured Output with Schema Reinforcement Learning [83.09230124049667]
  This study investigates the structured generation capabilities of large language models (LLMs) We find that the latest LLMs are still struggling to generate a valid string. Our models demonstrate significant improvement in both generating outputs and downstream tasks.
  arXiv  Detail & Related papers  (2025-02-26T06:45:29Z)
• EpiCoder: Encompassing Diversity and Complexity in Code Generation [49.170195362149386]
  We introduce a novel feature tree-based synthesis framework inspired by Abstract Syntax Trees (AST)<n>Unlike AST, which captures syntactic structure of code, our framework models semantic relationships between code elements.<n>We fine-tuned widely-used base models to create the EpiCoder series, achieving state-of-the-art performance at both the function and file levels.
  arXiv  Detail & Related papers  (2025-01-08T18:58:15Z)
• StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs [78.84060166851805]
  StructTest is a novel benchmark that evaluates large language models on their ability to produce structured outputs.<n>We demonstrate that StructTest serves as a good proxy for general reasoning abilities.
  arXiv  Detail & Related papers  (2024-12-23T22:08:40Z)
• LLM as a code generator in Agile Model Driven Development [1.12646803578849]
  This research champions Model Driven Development (MDD) as a viable strategy to overcome these challenges. We propose an Agile Model Driven Development (AMDD) approach that employs GPT4 as a code generator. Applying GPT4 auto generation capabilities yields Java and Python code that is compatible with the JADE and PADE frameworks.
  arXiv  Detail & Related papers  (2024-10-24T07:24:11Z)
• Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs [57.27982780697922]
  Large language models have demonstrated exceptional capability in natural language understanding and generation. However, their generation speed is limited by the inherently sequential nature of their decoding process. This paper introduces Lexical Unit Decoding, a novel decoding methodology implemented in a data-driven manner.
  arXiv  Detail & Related papers  (2024-05-24T04:35:13Z)
• COLLIE: Systematic Construction of Constrained Text Generation Tasks [33.300039566331876]
  COLLIE is a grammar-based framework that allows the specification of rich, compositional constraints with diverse generation levels. We develop tools for automatic extraction of task instances given a constraint structure and a raw text corpus. We perform systematic experiments across five state-of-the-art instruction-tuned language models and analyze their performances to reveal shortcomings.
  arXiv  Detail & Related papers  (2023-07-17T17:48:51Z)
• Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning [27.59524153097858]
  grammar-constrained decoding (GCD) can be used to control the generation of large language models (LMs) GCD can serve as a unified framework for structured NLP tasks in general. We show that grammar-constrained LMs substantially outperform unconstrained LMs or even beat task-specific finetuned models.
  arXiv  Detail & Related papers  (2023-05-23T11:54:37Z)
• ICE-Score: Instructing Large Language Models to Evaluate Code [7.556444391696562]
  We propose textttICE-Score, a new evaluation metric via instructing large language models for code assessments. Our metric addresses the limitations of existing approaches by achieving superior correlations with functional correctness and human preferences. Our results demonstrate that our metric surpasses state-of-the-art metrics for code generation.
  arXiv  Detail & Related papers  (2023-04-27T16:38:17Z)
• ReCode: Robustness Evaluation of Code Generation Models [90.10436771217243]
  We propose ReCode, a comprehensive robustness evaluation benchmark for code generation models. We customize over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. With human annotators, we verified that over 90% of the perturbed prompts do not alter the semantic meaning of the original prompt.
  arXiv  Detail & Related papers  (2022-12-20T14:11:31Z)
• A Simple, Yet Effective Approach to Finding Biases in Code Generation [16.094062131137722]
  This work shows that current code generation systems exhibit undesired biases inherited from their large language model backbones. We propose the "block of influence" concept, which enables a modular decomposition and analysis of the coding challenges.
  arXiv  Detail & Related papers  (2022-10-31T15:06:15Z)
• COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics [69.8062252611486]
  Cold decoding is a flexible framework that can be applied directly to off-the-shelf left-to-right language models. Our experiments on constrained generation tasks point to the effectiveness of our approach, both in terms of automatic and human evaluation.
  arXiv  Detail & Related papers  (2022-02-23T18:59:27Z)
• An Integer Linear Programming Framework for Mining Constraints from Data [81.60135973848125]
  We present a general framework for mining constraints from data. In particular, we consider the inference in structured output prediction as an integer linear programming (ILP) problem. We show that our approach can learn to solve 9x9 Sudoku puzzles and minimal spanning tree problems from examples without providing the underlying rules.
  arXiv  Detail & Related papers  (2020-06-18T20:09:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.