Imagen de Portada

Designing large language model prompts to extract scores from messy text: A shared dataset and challenge

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Thelwall, Mike
Formato:	Preprint
Publicado:	2026
Materias:	Digital Libraries Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Evaluating the Predictive Capacity of ChatGPT for Academic Peer Review Outcomes Across Multiple Platforms
por: Thelwall, Mike, et al.
Publicado: (2024)

Can social media provide early warning of retraction? Evidence from critical tweets identified by human annotation and large language models
por: Zheng, Er-Te, et al.
Publicado: (2024)

How much are LLMs changing the language of academic papers after ChatGPT? A multi-database and full text analysis
por: Kousha, Kayvan, et al.
Publicado: (2025)

Prompt perturbation and fraction facilitation sometimes strengthen Large Language Model scores
por: Thelwall, Mike
Publicado: (2025)

In which fields do ChatGPT scores align better than citations with research quality?
por: Thelwall, Mike
Publicado: (2025)

Have LLM-associated terms increased in article full texts in all fields?
por: Thelwall, Mike, et al.
Publicado: (2026)

Reading the unreadable: Creating a dataset of 19th century English newspapers using image-to-text language models
por: Bourne, Jonathan
Publicado: (2025)

Unsupervised extraction of local and global keywords from a single text
por: Aleksanyan, Lida, et al.
Publicado: (2023)

Developing ChemDFM as a large language foundation model for chemistry
por: Zhao, Zihan, et al.
Publicado: (2024)

Do Large Language Models know Which Published Articles have been Retracted?
por: Thelwall, Mike
Publicado: (2026)

Quantitative Methods in Research Evaluation Citation Indicators, Altmetrics, and Artificial Intelligence
por: Thelwall, Mike
Publicado: (2024)

Research quality evaluation by AI in the era of Large Language Models: Advantages, disadvantages, and systemic effects
por: Thelwall, Mike
Publicado: (2025)

Estimating the quality of academic books from their descriptions with ChatGPT
por: Thelwall, Mike, et al.
Publicado: (2025)

Implicit and Explicit Research Quality Score Probabilities from ChatGPT
por: Thelwall, Mike, et al.
Publicado: (2025)

Will AI be overconfident about academic research findings when reliant on abstracts? (v1)
por: Thelwall, Mike
Publicado: (2026)

Journal Quality Factors from ChatGPT: More meaningful than Impact Factors?
por: Thelwall, Mike, et al.
Publicado: (2024)

Can ChatGPT evaluate research quality?
por: Thelwall, Mike
Publicado: (2024)

Evaluating Research Quality with Large Language Models: An Analysis of ChatGPT's Effectiveness with Different Settings and Inputs
por: Thelwall, Mike
Publicado: (2024)

Can Smaller Large Language Models Evaluate Research Quality?
por: Thelwall, Mike
Publicado: (2025)

A Global South Strategy for Evaluating Research Value with ChatGPT
por: Nunkoo, Robin, et al.
Publicado: (2025)

High-performance automated abstract screening with large language model ensembles
por: Sanghera, Rohan, et al.
Publicado: (2024)

Which stylistic features fool ChatGPT research evaluations?
por: Kousha, Kayvan, et al.
Publicado: (2026)

Can Large Language Models Evaluate Grant Proposal Quality? Revisiting the Wennerås and Wold Peer Review Data
por: Sandström, Ulf, et al.
Publicado: (2026)

Is OpenAlex Suitable for Research Quality Evaluation and Which Citation Indicator is Best?
por: Thelwall, Mike, et al.
Publicado: (2025)

Research evaluation with ChatGPT: Is it age, country, length, or field biased?
por: Thelwall, Mike, et al.
Publicado: (2024)

In which fields can ChatGPT detect journal article quality? An evaluation of REF2021 results
por: Thelwall, Mike, et al.
Publicado: (2024)

Can ChatGPT evaluate research environments? Evidence from REF2021
por: Kousha, Kayvan, et al.
Publicado: (2025)

Can Small and Reasoning Large Language Models Score Journal Articles for Research Quality and Do Averaging and Few-shot Help?
por: Thelwall, Mike, et al.
Publicado: (2025)

Assessing the societal influence of academic research with ChatGPT: Impact case study evaluations
por: Kousha, Kayvan, et al.
Publicado: (2024)

Can ChatGPT be a good follower of academic paradigms? Research quality evaluations in conflicting areas of sociology
por: Thelwall, Mike, et al.
Publicado: (2025)

How is science discussed on Bluesky?
por: Zheng, Er-Te, et al.
Publicado: (2025)

Towards understanding evolution of science through language model series
por: Dong, Junjie, et al.
Publicado: (2024)

Institutional Books 1.0: A 242B token dataset from Harvard Library's collections, refined for accuracy and usability
por: Cargnelutti, Matteo, et al.
Publicado: (2025)

Large language models for automated scholarly paper review: A survey
por: Zhuang, Zhenzhen, et al.
Publicado: (2025)

Automated Generation of Research Workflows from Academic Papers: A Full-text Mining Framework
por: Zhang, Heng, et al.
Publicado: (2025)

Impact of large language models on peer review opinions from a fine-grained perspective: Evidence from top conference proceedings in AI
por: Wu, Wenqing, et al.
Publicado: (2026)

Large Language Models for Departmental Expert Review Quality Scores
por: Langfeldt, Liv, et al.
Publicado: (2026)

Evaluating the quality of published medical research with ChatGPT
por: Thelwall, Mike, et al.
Publicado: (2024)

Do male leading authors retract more articles than female leading authors?
por: Zheng, Er-Te, et al.
Publicado: (2025)

De-identification of clinical free text using natural language processing: A systematic review of current approaches
por: Kovačević, Aleksandar, et al.
Publicado: (2023)