Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models

• URL: http://arxiv.org/abs/2608.19025v1
• Date: Wed, 19 Aug 2026 15:20:11 GMT
• Title: Self-prompting and cross-model consensus enable reproducible data extraction from scientific literature with large language models
• Abstract summary: Browser-based large language models (LLMs) extract highly contextualized information from research articles.<n>We demonstrate four escalating stages of curation: expert curated prompts, simple instructions, autonomous discovery of literature and new datasets.<n>These findings define an auditable division of labour in which experts specify the evidence standard, models cross-check repeated extractions and researchers resolve disputed cases.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurately extracting nuanced, contextualized data from research articles is laborious and time intensive. Here, we investigate the performance of frontier, browser-based large language models (LLMs) to extract highly contextualized information. We demonstrate four escalating workflows, 1) given an expert curated prompt and research articles, most frontier LLMs perform well at data extraction, however can struggle with interpreting scientific context and nuance, 2) given simple instructions, LLMs can author their own prompts which were almost as eNective as expert-written prompts, 3) autonomous discovery of research literature was diNicult, agents either missed or hallucinated references, and 4) LLMs can create new datasets from published guidelines that closely match human-expert judges, but still require a human-in-the-loop. Together, these findings define an auditable division of labour in which experts specify the evidence standard, models cross-check repeated extractions and researchers resolve disputed cases, providing a practical route to scaling scientific data curation without relinquishing expert oversight.

Related papers

• A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization [14.654160505140426]
  We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates AI, large language models, and human scientists.<n>The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability.<n>It generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement.
  arXiv  Detail & Related papers  (2026-04-01T22:58:42Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• Who Gets Cited Most? Benchmarking Long-Context Language Models on Scientific Articles [81.89404347890662]
  SciTrek is a novel question-answering benchmark designed to evaluate the long-context reasoning capabilities of large language models (LLMs) using scientific articles.<n>Our analysis reveals systematic shortcomings in models' abilities to perform basic numerical operations and accurately locate specific information in long contexts.
  arXiv  Detail & Related papers  (2025-09-25T11:36:09Z)
• How Do LLM-Generated Texts Impact Term-Based Retrieval Models? [76.92519309816008]
  This paper investigates the influence of large language models (LLMs) on term-based retrieval models.<n>Our linguistic analysis reveals that LLM-generated texts exhibit smoother high-frequency and steeper low-frequency Zipf slopes.<n>Our study further explores whether term-based retrieval models demonstrate source bias, concluding that these models prioritize documents whose term distributions closely correspond to those of the queries.
  arXiv  Detail & Related papers  (2025-08-25T06:43:27Z)
• Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim $\rightarrow$ Evidence Reasoning [6.043212666944194]
  We present CLAIM-BENCH, a benchmark for evaluating large language models' capabilities in scientific claim-evidence extraction and validation.<n>We show that closed-source models like GPT-4 and Claude consistently outperform open-source counterparts in precision and recall.<n> strategically designed three-pass and one-by-one prompting approaches significantly improve LLMs' abilities to accurately link dispersed evidence with claims.
  arXiv  Detail & Related papers  (2025-06-09T21:04:39Z)
• Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models [52.439289085318634]
  We show how to identify training data known to proprietary large language models (LLMs) by using information-guided probes.<n>Our work builds on a key observation: text passages with high surprisal are good search material for memorization probes.
  arXiv  Detail & Related papers  (2025-03-15T10:19:15Z)
• Human-artificial intelligence teaming for scientific information extraction from data-driven additive manufacturing research using large language models [3.0061386772253784]
  Data-driven research in Additive Manufacturing (AM) has gained significant success in recent years. This has led to a plethora of scientific literature to emerge. It requires substantial effort and time to extract scientific information from these works. We propose a framework that enables collaboration between AM and AI experts to continuously extract scientific information from data-driven AM literature.
  arXiv  Detail & Related papers  (2024-07-26T15:43:52Z)
• SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literature [97.31347312130119]
  SciRIFF (Scientific Resource for Instruction-Following and Finetuning) is a dataset of 137K instruction-following instances for training and evaluation, covering 54 tasks.<n>These tasks span five core scientific literature understanding capabilities: information extraction, summarization, question answering, claim verification, and classification.<n> SciRIFF is unique in being entirely expert-written, high-quality instruction-following dataset for extracting and synthesizing information from research literature across diverse scientific fields.
  arXiv  Detail & Related papers  (2024-06-10T21:22:08Z)
• Exploring the Latest LLMs for Leaderboard Extraction [0.3072340427031969]
  This paper investigates the efficacy of different LLMs-ralMist 7B, Llama GPT-4-Turbo and GPT-4.o in extracting leaderboard information from empirical AI research articles. Our study evaluates the performance of these models in generating (Task, Metric, Score) quadruples from research papers.
  arXiv  Detail & Related papers  (2024-06-06T05:54:45Z)
• Had enough of experts? Quantitative knowledge retrieval from large language models [4.091195951668217]
  Large language models (LLMs) have been extensively studied for their abilities to generate convincing natural language sequences.<n>We introduce a framework that leverages LLMs to enhance Bayesian models by eliciting expert-like prior knowledge and imputing missing data.
  arXiv  Detail & Related papers  (2024-02-12T16:32:37Z)
• INTERS: Unlocking the Power of Large Language Models in Search with Instruction Tuning [59.07490387145391]
  Large language models (LLMs) have demonstrated impressive capabilities in various natural language processing tasks. Their application to information retrieval (IR) tasks is still challenging due to the infrequent occurrence of many IR-specific concepts in natural language. We introduce a novel instruction tuning dataset, INTERS, encompassing 20 tasks across three fundamental IR categories.
  arXiv  Detail & Related papers  (2024-01-12T12:10:28Z)
• Self-Verification Improves Few-Shot Clinical Information Extraction [73.6905567014859]
  Large language models (LLMs) have shown the potential to accelerate clinical curation via few-shot in-context learning. They still struggle with issues regarding accuracy and interpretability, especially in mission-critical domains such as health. Here, we explore a general mitigation framework using self-verification, which leverages the LLM to provide provenance for its own extraction and check its own outputs.
  arXiv  Detail & Related papers  (2023-05-30T22:05:11Z)

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.