What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction

• URL: http://arxiv.org/abs/2507.15152v1
• Date: Sun, 20 Jul 2025 23:09:04 GMT
• Title: What Level of Automation is "Good Enough"? A Benchmark of Large Language Models for Meta-Analysis Data Extraction
• Authors: Lingbo Li, Anuradha Mathrani, Teo Susnjak,
• Abstract summary: This study evaluates the practical performance of three LLMs across tasks involving statistical results, risk-of-bias assessments, and study-level characteristics.<n>We tested four distinct prompting strategies to determine how to improve extraction quality.<n> customised prompts were the most effective, boosting recall by up to 15%.
• Score: 0.3441021278275805
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Automating data extraction from full-text randomised controlled trials (RCTs) for meta-analysis remains a significant challenge. This study evaluates the practical performance of three LLMs (Gemini-2.0-flash, Grok-3, GPT-4o-mini) across tasks involving statistical results, risk-of-bias assessments, and study-level characteristics in three medical domains: hypertension, diabetes, and orthopaedics. We tested four distinct prompting strategies (basic prompting, self-reflective prompting, model ensemble, and customised prompts) to determine how to improve extraction quality. All models demonstrate high precision but consistently suffer from poor recall by omitting key information. We found that customised prompts were the most effective, boosting recall by up to 15\%. Based on this analysis, we propose a three-tiered set of guidelines for using LLMs in data extraction, matching data types to appropriate levels of automation based on task complexity and risk. Our study offers practical advice for automating data extraction in real-world meta-analyses, balancing LLM efficiency with expert oversight through targeted, task-specific automation.

Related papers

• RICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection [29.459431336830267]
  We propose a gradient-free method that quantifies the fine-grained contribution of individual samples to both task-level and global-level model performance.<n>We introduce a lightweight selection paradigm trained on RICo scores, enabling scalable data selection with a strictly linear inference complexity.
  arXiv  Detail & Related papers  (2025-05-08T15:17:37Z)
• MLLM-Selector: Necessity and Diversity-driven High-Value Data Selection for Enhanced Visual Instruction Tuning [69.7347209018861]
  We introduce MLLM-Selector, an automated approach that identifies valuable data for visual instruction tuning.<n>We calculate necessity scores for each sample in the VIT data pool to identify samples pivotal for enhancing model performance.<n>Our findings underscore the importance of mixing necessity and diversity in data choice, leading to the creation of MLLM-Selector.
  arXiv  Detail & Related papers  (2025-03-26T12:42:37Z)
• AD-LLM: Benchmarking Large Language Models for Anomaly Detection [50.57641458208208]
  This paper introduces AD-LLM, the first benchmark that evaluates how large language models can help with anomaly detection.<n>We examine three key tasks: zero-shot detection, using LLMs' pre-trained knowledge to perform AD without tasks-specific training; data augmentation, generating synthetic data and category descriptions to improve AD models; and model selection, using LLMs to suggest unsupervised AD models.
  arXiv  Detail & Related papers  (2024-12-15T10:22:14Z)
• Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning [71.2981957820888]
  We propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets. The framework initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. The generated data undergo a rigorous evaluation using a dual-model method that assesses both difficulty and quality.
  arXiv  Detail & Related papers  (2024-11-21T02:30:53Z)
• Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration [90.41908331897639]
  Large language models (LLMs) have significantly benefited from training on diverse, high-quality task-specific data. We present a novel approach, ReverseGen, designed to automatically generate effective training samples.
  arXiv  Detail & Related papers  (2024-10-22T06:43:28Z)
• AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning [93.96463520716759]
  Large language model (LLM) agents have demonstrated impressive capabilities in utilizing external tools and knowledge to boost accuracy and hallucinations. Here, we introduce AvaTaR, a novel and automated framework that optimize an LLM agent to effectively leverage provided tools, improving performance on a given task.
  arXiv  Detail & Related papers  (2024-06-17T04:20:02Z)
• Exploring the use of a Large Language Model for data extraction in systematic reviews: a rapid feasibility study [0.28318468414401093]
  This paper describes a rapid feasibility study of using GPT-4, a large language model (LLM), to (semi)automate data extraction in systematic reviews.<n>Overall, results indicated an accuracy of around 80%, with some variability between domains.
  arXiv  Detail & Related papers  (2024-05-23T11:24:23Z)
• Automatically Extracting Numerical Results from Randomized Controlled Trials with Large Language Models [19.72316842477808]
  We evaluate whether modern large language models (LLMs) can reliably perform this task. Massive LLMs that can accommodate lengthy inputs are tantalizingly close to realizing fully automatic meta-analysis.
  arXiv  Detail & Related papers  (2024-05-02T19:20:11Z)
• Large Language Models as Automated Aligners for benchmarking Vision-Language Models [48.4367174400306]
  Vision-Language Models (VLMs) have reached a new level of sophistication, showing notable competence in executing intricate cognition and reasoning tasks. Existing evaluation benchmarks, primarily relying on rigid, hand-crafted datasets, face significant limitations in assessing the alignment of these increasingly anthropomorphic models with human intelligence. In this work, we address the limitations via Auto-Bench, which delves into exploring LLMs as proficient curation, measuring the alignment betweenVLMs and human intelligence and value through automatic data curation and assessment.
  arXiv  Detail & Related papers  (2023-11-24T16:12:05Z)
• Impossible Distillation: from Low-Quality Model to High-Quality Dataset & Model for Summarization and Paraphrasing [59.58984194238254]
  We present Impossible Distillation, a novel framework for paraphrasing and sentence summarization. Unlike prior works that rely on an extreme-scale teacher model, we hypothesize and verify the paraphrastic proximity intrinsic to pre-trained LMs. By identifying and distilling generations from these subspaces, Impossible Distillation produces a high-quality dataset and model even from GPT2-scale LMs.
  arXiv  Detail & Related papers  (2023-05-26T05:19:24Z)

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.