What is a key risk or source of error when using LLMs in evidence synthesis, and how has this tool been specifically designed to address it? In what ways is this approach novel compared to other platforms?

What is a key risk or source of error when using LLMs in evidence synthesis, and how has this tool been specifically designed to address it? In what ways is this approach novel compared to other platforms?

A key risk associated with using LLMs in evidence synthesis is hallucination and loss of traceability—where the model generates confident but unsupported outputs, or introduces information that cannot be linked back to the source study. This is especially problematic in systematic reviews, where transparency, reproducibility, and auditability are critical.

EasySLR has been specifically designed to mitigate this risk. Across screening and full-text stages, we apply strong context and prompt constraints so the LLM operates only within the boundaries of the relevant citation or PDF, rather than drawing from general knowledge. In the Full-Text stage in particular, all AI outputs are explicitly linked back to source passages in the document, ensuring that no information is generated without a verifiable reference. This substantially reduces hallucinations and allows reviewers to quickly validate AI suggestions.

From a performance perspective, with the continuous improvement of LLMs over the past few years, we now regularly observe ~85–90% accuracy at the screening stages. However, rather than relying solely on raw model capability, EasySLR focuses on engineering safeguards—prompt optimisation, context control, and source grounding—to ensure stable and reliable behaviour.

What’s novel compared to many other platforms is that EasySLR was built as an AI-first system from day one, not as a traditional review platform with AI added later. This has allowed us to deeply integrate AI into the workflow, rather than treating it as an external add-on. In addition, we’ve invested heavily in usability and infrastructure, ensuring the platform remains responsive and easy to use even with large citation volumes—addressing everyday reviewer pain points such as speed, scalability, and setup complexity.


    • Related Articles

    • Using Tags in EasySLR

      Tags in EasySLR are a powerful way to categorize, annotate, and organize studies, enabling quick filtering and efficient navigation throughout the review process. They work across screening stages, can be blinded between reviewers, and provide ...
    • How to Bulk Upload PDFs using Zotero/Endnote?

      At EasySLR, we understand the importance of efficient workflow management, especially when handling extensive research literature. Our Bulk PDF Upload feature is designed to streamline your research process by allowing the seamless import of large ...
    • Using Multiple Filters in EasySLR

      EasySLR provides powerful filtering options to refine your search results, making the literature review process more efficient. By applying multiple filters, you can easily narrow down relevant studies based on a range of criteria such as Title, ...
    • Bulk PDF Uploads Using AI in EasySLR

      Direct PDF Matching in EasySLR allows users to automatically match and upload multiple full-text PDFs. This streamlines the process of linking full texts with citations—saving you time and effort during the full-text screening stage. Easily match and ...
    • Comparing AI Assistant and AI Reviewer in EasySLR

      EasySLR utilises advanced artificial intelligence to streamline and enhance the article screening process. Within the platform, two key AI features play pivotal roles: the AI Assistant and the AI Reviewer. While both are designed to enhance ...