Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models

• URL: http://arxiv.org/abs/2404.05893v4
• Date: Thu, 29 Aug 2024 21:34:22 GMT
• Title: Use of a Structured Knowledge Base Enhances Metadata Curation by Large Language Models
• Authors: Sowmya S. Sundaram, Benjamin Solomon, Avani Khatri, Anisha Laumas, Purvesh Khatri, Mark A. Musen,
• Abstract summary: Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs) to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository.
• Score: 2.186740861187042
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Metadata play a crucial role in ensuring the findability, accessibility, interoperability, and reusability of datasets. This paper investigates the potential of large language models (LLMs), specifically GPT-4, to improve adherence to metadata standards. We conducted experiments on 200 random data records describing human samples relating to lung cancer from the NCBI BioSample repository, evaluating GPT-4's ability to suggest edits for adherence to metadata standards. We computed the adherence accuracy of field name-field value pairs through a peer review process, and we observed a marginal average improvement in adherence to the standard data dictionary from 79% to 80% (p<0.5). We then prompted GPT-4 with domain information in the form of the textual descriptions of CEDAR templates and recorded a significant improvement to 97% from 79% (p<0.01). These results indicate that, while LLMs may not be able to correct legacy metadata to ensure satisfactory adherence to standards when unaided, they do show promise for use in automated metadata curation when integrated with a structured knowledge base

Related papers

• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4 [2.54365580380609]
  We investigate the application of large language models (LLMs) to scenarios involving the tradeoff between privacy and utility in tabular data. Our approach entails prompting GPT-4 by transforming data points into textual format, followed by the inclusion of precise sanitization instructions in a zero-shot manner. We find that this relatively simple approach yields performance comparable to more complex adversarial optimization methods used for managing privacy-utility tradeoffs.
  arXiv  Detail & Related papers  (2024-04-07T19:02:50Z)
• SMaRt: Improving GANs with Score Matching Regularity [94.81046452865583]
  Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex. We show that score matching serves as a promising solution to this issue thanks to its capability of persistently pushing the generated data points towards the real data manifold. We propose to improve the optimization of GANs with score matching regularity (SMaRt)
  arXiv  Detail & Related papers  (2023-11-30T03:05:14Z)
• KERMIT: Knowledge Graph Completion of Enhanced Relation Modeling with Inverse Transformation [19.31783654838732]
  We use large language models to generate coherent descriptions, bridging the semantic gap between queries and answers. We also utilize inverse relations to create a symmetric graph, thereby providing augmented training samples for KGC. Our approach achieves a 4.2% improvement in Hit@1 on WN18RR and a 3.4% improvement in Hit@3 on FB15k-237, demonstrating superior performance.
  arXiv  Detail & Related papers  (2023-09-26T09:03:25Z)
• Bring Your Own Data! Self-Supervised Evaluation for Large Language Models [52.15056231665816]
  We propose a framework for self-supervised evaluation of Large Language Models (LLMs) We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence. We find strong correlations between self-supervised and human-supervised evaluations.
  arXiv  Detail & Related papers  (2023-06-23T17:59:09Z)
• MetaEnhance: Metadata Quality Improvement for Electronic Theses and Dissertations of University Libraries [3.5761273302956282]
  We investigate methods to automatically detect, correct, and canonicalize scholarly metadata. We propose MetaEnhance, a framework that utilizes state-of-the-art artificial intelligence methods to improve the quality of these fields.
  arXiv  Detail & Related papers  (2023-03-30T18:56:42Z)
• Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations [58.442103936918805]
  We show that Attention Mask Consistency produces superior visual grounding results than previous methods. AMC is effective, easy to implement, and is general as it can be adopted by any vision-language model.
  arXiv  Detail & Related papers  (2022-06-30T17:55:12Z)
• Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of Summaries [59.27273928454995]
  Current pre-trained models applied to summarization are prone to factual inconsistencies which misrepresent the source text or introduce extraneous information. We create a crowdsourcing evaluation framework for factual consistency using the rating-based Likert scale and ranking-based Best-Worst Scaling protocols. We find that ranking-based protocols offer a more reliable measure of summary quality across datasets, while the reliability of Likert ratings depends on the target dataset and the evaluation design.
  arXiv  Detail & Related papers  (2021-09-19T19:05:00Z)
• Regularizing Models via Pointwise Mutual Information for Named Entity Recognition [17.767466724342064]
  We propose a Pointwise Mutual Information (PMI) to enhance generalization ability while outperforming an in-domain performance. Our approach enables to debias highly correlated word and labels in the benchmark datasets. For long-named and complex-structure entities, our method can predict these entities through debiasing on conjunction or special characters.
  arXiv  Detail & Related papers  (2021-04-15T05:47:27Z)
• DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks [88.62288327934499]
  We propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings.
  arXiv  Detail & Related papers  (2020-11-03T07:49:15Z)

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.