aiqbench analysis
This study benchmarks six AI tools against a rigorous 102-article corpus, revealing that while LLMs can assist in discovering and interpreting scientific literature, they frequently misclassify mentions and generate unsupported claims during synthesis. The research concludes that these models cannot replace expert judgment for evaluating evidence or finalizing research conclusions, offering eight practical recommendations for researchers integrating AI into their workflows.
Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark
arXiv:2611.05459v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support scientific literature reviews, yet evaluations often examine individual tasks rather than the review process as a whole. We assess six AI tools across four stages: finding relevant articles, interpreting them, synthesizing across them, and proposing future research. The benchmark is a published review of the Spanish plume weather pattern and its 102-article corpus. In the initial searches, five tools collectively identified 57 articles, with the best individual tool finding 42. Institutional library access increased discovery from 42 to 82 articles for Codex and from 15 to 79 for Claude Code. Given the complete corpus of 102 PDFs, three tools correctly identified all 18 articles discussing the Spanish plume substantially, but incorrectly classified 40% to 79% of the 84 passing mentions as substantial. The same three tools produced syntheses evaluated blindly by two domain experts. Although largely accurate, the syntheses provided limited insight and sometimes contained unsupported claims, quotation errors, and exaggerated statements of consensus. Finally, all three tools proposed research directions broader than the Spanish plume literature, although two approached questions identified in the benchmark review. No single tool performed best across all tasks. We provide eight recommendations for researchers using AI tools in literature reviews. Our findings suggest that LLMs can assist with discovering and interpreting scientific literature, particularly when institutional access is available, but cannot replace expert judgment in evaluating evidence or synthesizing research.
Title:Can Large Language Models Review the Scientific Literature? A Test Against a 102-Article Benchmark
Abstract:Large language models (LLMs) are increasingly used to support scientific literature reviews, yet evaluations often examine individual tasks rather than the review process as a whole. We assess six AI tools across four stages: finding relevant articles, interpreting them, synthesizing across them, and proposing future research. The benchmark is a published review of the Spanish plume weather pattern and its 102-article corpus. In the initial searches, five tools collectively identified 57 articles, with the best individual tool finding 42. Institutional library access increased discovery from 42 to 82 articles for Codex and from 15 to 79 for Claude Code. Given the complete corpus of 102 PDFs, three tools correctly identified all 18 articles discussing the Spanish plume substantially, but incorrectly classified 40% to 79% of the 84 passing mentions as substantial. The same three tools produced syntheses evaluated blindly by two domain experts. Although largely accurate, the syntheses provided limited insight and sometimes contained unsupported claims, quotation errors, and exaggerated statements of consensus. Finally, all three tools proposed research directions broader than the Spanish plume literature, although two approached questions identified in the benchmark review. No single tool performed best across all tasks. We provide eight recommendations for researchers using AI tools in literature reviews. Our findings suggest that LLMs can assist with discovering and interpreting scientific literature, particularly when institutional access is available, but cannot replace expert judgment in evaluating evidence or synthesizing research.
34 pages, 7 figures, 6 tables. Data, prompts, analysis scripts and results: this https URL (GitHub: this https URL)
Artificial Intelligence (cs.AI); Digital Libraries (cs.DL)
arXiv:2611.05459 [cs.AI]
(or arXiv:2611.05459v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2611.05459 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 363 words
Related coverage
A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization
arXiv · Sep 1, 2026
An Autonomous Scientific Knowledge Generation Framework for AI-Driven Scientific Discovery
arXiv · Aug 5, 2026
LitCurate: A Configuration-Driven AI-Assisted Framework for Scientific Database Construction with an Application to Lower-Mantle Equation-of-State Data
arXiv · Sep 1, 2026
RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature
arXiv · Aug 28, 2026