Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2607.25965

Is ChatGPT as reliable as individual reviewers assessing the quality of published journal articles from PDFs or titles and abstracts?

Mike Thelwall·Parveen Ali
View original source ↗Read source document ↗Export metadata ↓

Abstract

Whilst Large Language Models (LLMs) have a weak to moderate ability to score published journal articles for research quality, they have not been compared with individual expert reviewers. It is also unknown whether quality scores from ChatGPT based on PDFs can improve on those from titles and abstracts through a deeper evaluation. To address both issues, this article uses expert scores (98 internal departmental ratings for UK Unit of Assessment [UoA] 3 Allied Health Professions, 44 for UoA13 Architecture, and 58 library and information science articles from UoA34), comparing them against ChatGPT-5.4 scores from both title/abstract and PDF inputs. For UoA3, individual reviewer scores were also compared against each other and ChatGPT-5.4. The rank correlations with expert scores are almost all statistically significantly positive, but differences between the correlations are mostly not, despite weakly suggesting that ChatGPT-5.4 can be more reliable than individual reviewers for UoA3. Moreover, whilst ChatGPT-5.4 provides more detailed evaluations of PDFs than of titles/abstracts, its score predictions do not seem to improve. Thus, whilst the results broadly confirm the value of ChatGPT scores for ranking academic documents, its apparently deeper evaluative comments on PDFs are misleading in the sense of not translating to improved score predictions.

Explore related subjects

cs.DL

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Mike Thelwall, Parveen Ali. 2026-07-28. Is ChatGPT as reliable as individual reviewers assessing the quality of published journal articles from PDFs or titles and abstracts?. https://arxiv.org/abs/2607.25965

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

From Funding to Findings (FIND): An Open Database of NSF Awards and Research Outputs

Public funding plays a central role in driving scientific discovery. To better understand the link between research inputs and outputs, we introduce FIND (Funding-Impact NSF Database), an open-access dataset that systematically links NSF grant proposals to their downstream research outputs, including publication metadata and abstracts. The primary contribution of this project is the creation of a large-scale, structured dataset that enables transparency, impact evaluation, and metascience research on the returns to public funding. To illustrate the potential of FIND, we present two proof-of-concept NLP applications. First, we analyze whether the language of grant proposals can predict the subsequent citation impact of funded research. Second, we leverage large language models to extract scientific claims from both proposals and resulting publications, allowing us to measure the extent to which funded projects deliver on their stated goals. Together, these applications highlight the utility of FIND for advancing metascience, informing funding policy, and enabling novel AI-driven analyses of the scientific process.

cs.DL↗
arXiv2026

Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific Revolutions

We introduce document embedding geometry as a quantitative observable of conceptual reorganization and develop a counterfactual ablation framework for measuring how individual concepts influence the organization of scientific knowledge, providing a quantitative framework for detecting scientific revolutions. The observable is defined by the geometric perturbation induced when removing documents associated with a candidate concept from the embedding space before and after its historical emergence. Statistical validation is performed using five historical case studies spanning physics, mathematics, and machine learning: special relativity, Gödel's incompleteness theorems, the Higgs mechanism, deep learning, and the attention mechanism underlying transformer architectures. Across the historical case studies, the framework identifies measurable geometric signatures associated with conceptual reorganization, while the validation studies expose important limitations arising from document assignment and sparse historical data. These results establish embedding geometry as a medium for quantifying conceptual reorganization, providing a new approach for studying how scientific fields restructure over time.

cs.DL↗
arXiv2026

Toward non-textual representation of social anthropology: Modeling cultures as knowledge graphs

The study examines the emerging field of knowledge representation in the context of the semantic web and linked data, with a focus on knowledge produced within the social sciences - particularly in sociocultural anthropology. It starts from the premise that natural language, especially its textualized form, has long been the primary vehicle for producing and communicating anthropological research. Informed by theoretical approaches from information science, the study explores how computational methods may offer alternative modes of structuring and representing anthropological knowledge. It challenges the dominance of text as the sole representational medium and highlights the potential of semantic modeling to open new epistemological pathways. At the same time, it acknowledges the conceptual and methodological challenges involved in such a transition. This approach shifts emphasis away from metrics and programming, foregrounding processes of conceptualization, semantics, meaning, and reasoning as key to engaging with anthropological knowledge in digital environments.

cs.DL↗