Buchumschlag

Prompt perturbation and fraction facilitation sometimes strengthen Large Language Model scores

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Thelwall, Mike
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Digital Libraries
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Do Large Language Models know Which Published Articles have been Retracted?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

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

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

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

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

Designing large language model prompts to extract scores from messy text: A shared dataset and challenge
von: Thelwall, Mike
Veröffentlicht: (2026)

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

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

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

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

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

Can ChatGPT evaluate research quality?
von: Thelwall, Mike
Veröffentlicht: (2024)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Can news and social media attention reduce the influence of problematic research?
von: Zheng, Er-Te, et al.
Veröffentlicht: (2025)

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

Which international co-authorships produce higher quality journal articles?
von: Thelwall, Mike, et al.
Veröffentlicht: (2022)

Indo-US Research Collaboration: strengthening or declining?
von: Dua, Jyoti, et al.
Veröffentlicht: (2024)

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

Science discussions of retracted articles on Bluesky: public scrutiny or misinformation spreading?
von: Zheng, Er-Te, et al.
Veröffentlicht: (2026)

Exploring the applicability of Large Language Models to citation context analysis
von: Nishikawa, Kai, et al.
Veröffentlicht: (2024)

Leveraging Large Language Models for Realizing Truly Intelligent User Interfaces
von: Oelen, Allard, et al.
Veröffentlicht: (2025)

Towards Development of Automated Knowledge Maps and Databases for Materials Engineering using Large Language Models
von: Prasad, Deepak, et al.
Veröffentlicht: (2024)

Expert-Grounded Automatic Prompt Engineering for Extracting Lattice Constants of High-Entropy Alloys from Scientific Publications using Large Language Models
von: Liu, Shunshun, et al.
Veröffentlicht: (2025)

Prompt engineering for bibliographic web-scraping
von: Blázquez-Ochando, Manuel, et al.
Veröffentlicht: (2026)

A Stylometric Application of Large Language Models
von: Stropkay, Harrison F., et al.
Veröffentlicht: (2025)