Scientific Knowledge Discovery in the Age of Large Language Models

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Eleni Adamidi, Serafeim Chatzopoulos, Thanasis Vergoulis
• Venue: arXiv: cs.DL
• Published: 2026-07-29
• Collected: 2026-07-30
• URL: http://arxiv.org/abs/2607.26670v1
• PDF: https://arxiv.org/pdf/2607.26670v1
• DOI: UNKNOWN

Plain-Language Brief

This research paper reviews 34 peer-reviewed studies that use generative large language models (LLMs) for literature retrieval and screening of candidate studies against eligibility criteria. The study identifies these papers through a Boolean search over the OpenAIRE Graph.

What the Document Says

• The rapid growth of scholarly literature makes it difficult to identify relevant publications.
• Conventional search systems rely heavily on manually formulated queries and manual inspection.
• Generative LLMs offer an alternative for literature retrieval and screening of candidate studies.
• 34 peer-reviewed papers using generative LLMs were reviewed.
• These papers were identified through a Boolean search over the OpenAIRE Graph.
• The review focuses on the LLMs employed, model access and adaptation, prompting and architectural techniques, ground-truth sources, and evaluation metrics.

Key Concepts Mentioned

• generative large language models
• literature retrieval
• screening of candidate studies
• Boolean search
• OpenAIRE Graph

Claims Made by the Document

• Generative LLMs offer a more flexible alternative for literature retrieval and screening.
• 34 peer-reviewed papers using generative LLMs were identified.

Evidence Used

• Rapid growth of scholarly literature
• Difficulty in identifying relevant publications
• Conventional search systems
• Manually formulated queries and manual inspection
• Generative LLMs
• 34 peer-reviewed papers
• Boolean search over the OpenAIRE Graph

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

The rapid growth of scholarly literature has made identifying relevant publications increasingly difficult, and conventional search systems still depend heavily on manually formulated queries and effortful manual inspection. Generative large language models (LLMs) offer a more flexible alternative, supporting literature retrieval and the screening of candidate studies against eligibility criteria. This chapter surveys 34 peer-reviewed papers applying generative LLMs to these two tasks, identified via a Boolean search over the OpenAIRE Graph (1,589 records screened to 34 inclusions). Reviewed studies are characterised by LLMs employed, model access and adaptation, prompting and architectural techniques, ground-truth sources, and evaluation metrics.