AI Evaluations - Library

Consensus - Library AI Evaluation

This evaluation is part of Deakin Library’s AI Evaluation series, providing structured, practice-informed insights into emerging AI technologies. Evaluations are designed to support critical decision-making and responsible engagement with AI, guided by Deakin’s Generative AI Framework and Principles.

Our findings and assessment are shared to inform your judgement. Evaluations are not an endorsement.

Evaluations like this one are not about deciding whether the AI “works,” but about understanding what kind of thinking and behaviours it encourages and whether that aligns with our pedagogical, scholarly, and professional values.

Consensus overview

Summary findings

Evaluation snapshot

• Consensus is a semantic academic search tool designed to support exploratory, question-led research.e.
• Draws from publicly available abstracts via Semantic Scholar, OpenAlex, and additional academic content aggregated through its own data collection.
• Cited claims are extracted and summarised, with a “Consensus meter” visualising where research appears to align.
• Outputs are predominantly based on abstracts rather than full-text synthesis. 
• Supports exploratory academic inquiry but lacks the depth, transparency, and reproducibility required for systematic review-level research.

Benefits

• Uses semantic search and NLP (Natural Language Processing) to rapidly extract, summarise, and display consensus-level insights from academic literature.
• Helps users quickly orient in a research topic by surfacing relevant studies and linked citations.
• “Consensus meter” provides a novel way to visualise scholarly agreement, encouraging question refinement.
• Encourages evidence awareness and citation searching by linking directly to peer-reviewed sources. 
• Intuitive interface and familiar functionality require minimal onboarding and training.
• Supports export to common reference management tools like Zotero and EndNote (Deakin’s preferred bibliographic software). 
• Encourages question refinement and engagement with scholarly consensus, providing a low-barrier entry point to research.  
• Institutional subscription model available, with potential use in academic skills and research training contexts. 

Limitations or risks

• Reliance on abstracts limits access to context, methodological detail, and full-text analysis, regardless of whether the articles are Open Access. 
• Visualisation methods lack clarity; users are not told how “consensus” is measured or calculated, which can lead to misinterpretation.
• Simplified summaries may obscure scholarly disagreement, nuance, or discipline-specific reasoning. 
• Over-reliance on summarised claims may discourage deeper reading or critical engagement with full texts.
• The “Ask Paper” feature allows PDF uploads, which may introduce copyright risk. Some publishers restrict the use of AI with their content. Users need to check licences or terms before uploading into Consensus. Contact your librarian for help.
• Vendor information on data sources, model training, and retention is limited. Privacy policy, in particular contains ambiguous clauses.
• Indexed content coverage is strongest in science, technology, health, and medical research; with more limited representation in other disciplines. 
• While well-suited to scoping and topic familiarisation, the tool lacks the transparency, methodological depth, and reproducibility required for systematic reviews or advanced synthesis work. 

Notable points

• Consensus states the tool is designed for exploratory, question-led research, not for producing evidence syntheses or systematic reviews. 
•  Although it may appear to provide answers, it instead surfaces literature summaries and indicates where research aligns or diverges, rather than offering definitive conclusions. 
• Best used as supplement to, not a substitute for, expert search strategies, full-text reading, and critical reading strategies. 
• Already informally used by academics in higher education, including Deakin, though it is not currently licensed institutionally. 
• Aligns with open scholarship principles through citation traceability but is not integrated with institutional discovery systems. 
• Consensus meter is a distinctive feature but must be framed carefully, as it does not account for dissenting perspectives or explain how agreement is measured.

Considerations and implications

This section surfaces key reflections from the evaluation, moving beyond tool description to sense-making. It considers how AI may influence library practice, sector responsibilities, and the broader information landscape. As a boundary-spanning part of the university, the Library draws on its expertise in information practice and knowledge management to surface impacts across cohorts.

Our insights are provisional and reflective, emphasising conditions and contexts rather than certainties or prescriptions.

Our role is not to endorse tools like Consensus but to make meaning. To examine how different forms of AI may reshape how information is produced, accessed, and understood. These considerations are part of the academic library’s role in supporting the organisation, interrogation, and circulation of knowledges within our academic contexts.

Click on the plus (+) icons below to explore considerations related to digital literacies, user behaviours and needs, educator capability, open practices, and library practices: