cs.CLSep 5, 2026

Checkpoints Are Not Enough: Trust Calibration in CoSLR, a Human-AI System for Systematic Literature Reviews

Authors: MD Aidul Islam, Malik Abdul Sami, Muhammad Waseem, Zeeshan Rasheed, Kai-kristian Kemell, Zheying Zhang, Pekka Abrahamsson

Organizations: Tampere University, Tampere, Finland

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Systematic Literature Reviews (SLRs) are essential for evidence-based research but remain time-consuming, requiring researchers to manage large volumes of publications across planning, screening, analysis, and reporting. Large language models (LLMs) can now produce fluent, well-structured review text, which makes it difficult to distinguish synthesis that was verified by a researcher from synthesis that merely appears authoritative. This raises the risk that unverified AI-generated synthesis enters the scholarly record carrying the credibility of a systematic review. We present CoSLR, a Human-AI collaborative multi-agent system that supports the SLR workflow through a modular three-phase pipeline using large language models and Retrieval-Augmented Generation (RAG), and that places explicit, mandatory human checkpoints on the path between generated output and its acceptance. In a survey-based study with 63 participants, the system was received positively: 27 of 63 participants (42.9 percent) rated its usability highly, indicating that the mandatory checkpoints did not come at the cost of a workable interface. However, a checkpoint safeguards the review only if researchers use it to verify: 22 of 63 participants (34.9 percent) reported that they would trust AI-generated summaries and reports without additional human checking after only a short interaction with the system. These findings indicate that Human-AI collaboration can support literature review work, but that the effectiveness of human oversight depends on whether users are willing to exercise it. This is a calibration problem that interface design must address directly, not assume.

Figures & tables

Study / ToolAutomation FocusTechniques UsedMain Limitation
Abstrackr ( Wallace et al., 2010 )Title and abstract screeningSupervised machine learning with user feedbackRequires substantial manual labeling and offers limited explainability.
ASReview ( van de Schoot et al., 2021 )Screening prioritizationActive learning with text-based rankingAutomates mainly one phase of the review workflow.
Rayyan ( Ouzzani et al., 2016 )Collaborative screening supportWorkflow management and relevance filteringPrimarily a decision-support platform rather than full automation.
DistillerSR ( Hamel et al., 2020 )Review workflow managementMachine learning-assisted prioritizationDepends on human review for final decisions.
RobotReviewer ( Marshall et al., 2016 )Risk-of-bias assessment and extractionNLP and machine learningStrongly domain-specific to biomedical evidence synthesis.
EPPI-Reviewer ( Thomas et al., 2023 )Screening and review managementAutomation-supported review workflow toolsLimited end-to-end intelligence across the full review lifecycle.
Table 1. Comparison of representative works on systematic literature review automation
Figure 1. The SLR process and the points of Human–AI collaboration. Following the Kitchenham and Charters lifecycle ( Kitchenham and Charters, 2007 ) , the review proceeds top to bottom through the stages shown on the left. For each stage, the centre column names the AI agent that produces a draft output and the right column states the researcher’s role. Amber boxes denote mandatory human checkpoints, where a researcher decision is required before the workflow proceeds; dashed boxes denote lighter human oversight. Double-headed arrows indicate the propose–validate cycle that keeps the researcher in control throughout. A workflow diagram of the Systematic Literature Review process. The diagram shows SLR stages arranged vertically, corresponding AI agents that support each stage, and researcher responsibilities. Mandatory human checkpoints and lighter oversight points are marked to show where researchers validate AI-generated outputs.
Figure 2. High-level architecture of the proposed Human–AI collaborative system for automating Systematic Literature Reviews (SLRs). The system is organized into three phases: (1) planning and retrieval, where LLM agents generate research objectives, research questions, and search queries; (2) ingestion and indexing, where retrieved and uploaded papers are processed, chunked, embedded, and stored in a vector index; and (3) grounded interaction and reporting, where retrieval-augmented generation (RAG) enables evidence-grounded analysis and automated report generation. Human checkpoints and trace logs ensure transparency, validation, and reproducibility throughout the workflow. A high-level architecture diagram of the proposed Human–AI collaborative SLR system. The diagram shows three main phases: planning and retrieval, ingestion and indexing, and grounded interaction and reporting. It also shows LLM agents, document processing, vector indexing, retrieval-augmented generation, human checkpoints, and trace logs that support transparency and validation.
Figure 3. RAG-based interactive analysis component used in the proposed system, adapted from Hasan et al. ( Hasan et al., 2025 ) . User queries are matched against indexed document embeddings to retrieve relevant evidence, which is then provided to the language model to generate grounded responses in the interactive query interface. A retrieval-augmented generation component diagram. The diagram shows a user query being converted into an embedding, matched against indexed document embeddings, and used to retrieve relevant evidence passages. The retrieved evidence is provided to a language model, which generates a grounded response for the interactive query interface.
SectionFocus / Measured DimensionNo. of QuestionsQuestion Type
Demographic InformationCaptures participant role, document usage frequency, explored content, and usage setting.4Categorical / multiple choice
Usability and InteractionEvaluates support for defining research objectives and questions, generating search strings, screening articles, report generation, and question-answering interaction.10Likert-scale / binary
Cognitive Load & User ExperienceMeasures mental demand, uncertainty during use, and whether the system reduces technical handling effort.3Likert-scale
Learning & RetentionAssesses perceived support for understanding material, identifying key concepts, and improving confidence in discussing or applying content.3Likert-scale
Productivity and WorkflowEvaluates perceived accuracy, usefulness of summaries, efficiency, time savings, retrieval breadth, risk of missing studies, and preferred level of manual intervention.8Likert-scale / categorical
Recommendation & ConcernsCaptures adoption intention, preference over traditional approaches, and privacy, security, or ethical concerns.3Likert-scale / binary
Table 2. Structure of the post-interaction questionnaire
Figure 4. Distribution of participant roles reported in the evaluation study. Because respondents could select multiple roles, several role combinations are present. A bar chart showing the distribution of participant roles in the evaluation study. The chart reports the number of respondents who selected each role, such as researcher, student, professional, and teacher. Since participants could select more than one role, the counts are not mutually exclusive.
Response ExcerptInitial Code
“Add more data sources like IEEE”More data sources
“Search string need to be more precise”Query precision
“The created report properly cited the papers”Citation traceability
“Would like a few more and clearer checkpoints”Manual checkpoints
Table 3. Illustrative examples of initial coding in the qualitative analysis
Code GroupExample CodesRelated Theme
Planning supportRQ generation, objective formulation, search query generationSupport for RQs and search formulation
Synthesis supportreport generation, data extraction, structured output, summariesReport generation and synthesis support
Retrieval limitationsmore data sources, query precision, missing papers, direct PDF accessRetrieval quality and coverage
Evidence transparencycitation traceability, source visibility, seeing analyzed papersTransparency and evidence traceability
User controlmanual checkpoints, workflow separation, validation control, context access issuesWorkflow control and manual checkpoints
Table 4. Illustrative code groups used in the qualitative analysis
DimensionRepresentative itemsAvg. Mean
UsabilityQ&A interaction, report generation, responsiveness, objective/RQ framing, data extraction3.78
Learning supportUnderstanding material, key concepts, confidence in applying content3.68
ProductivityAnswer accuracy, report summaries, comprehension support3.68
Trust & oversightTrust in generated outputs without human checking3.02
Table 5. Grouped descriptive summary of Likert-scale responses
ItemMeanVar.SD
Ease of Q&A interaction3.620.790.89
Report generation intuitiveness3.710.660.81
Responsiveness / speed3.900.800.89
Relevance / accuracy of answers3.570.800.89
Trust without human checking3.021.241.11
Table 6. Descriptive statistics for selected Likert-scale items (N=63)
Figure 5. Distribution of perceived time savings reported by participants when using the proposed SLR automation system. A bar chart showing participants' perceived time savings when using the proposed SLR automation system. The chart compares three categories of reported time savings: less than 25 percent, 25 to 50 percent, and more than 50 percent.
ThemeDescriptionImplication
Support for research question and search formulationParticipants valued the system’s ability to generate research questions, objectives, and search strings.Indicates perceived usefulness in the planning stage of the SLR workflow.
Report generation and synthesis supportUsers appreciated automated synthesis, report generation, and data extraction features.Suggests that the system is especially valuable for analysis and structured reporting.
Retrieval quality and coverageParticipants requested broader database integration and more precise search strings.Highlights retrieval as a key limitation and a priority for future improvement.
Transparency and evidence traceabilityUsers wanted clearer links between generated outputs and the papers used as evidence.Reinforces the importance of evidence grounding and explainability in Human–AI systems.
Workflow control and manual checkpointsSeveral responses emphasized the need for stronger workflow control and manual validation.Supports the value of human-in-the-loop design rather than full black-box automation.
Table 7. Themes identified from open-ended survey responses
Figure 6. Distribution of trust in AI-generated output without additional human checking (1 = very low, 5 = very high), overall and split by whether the participant selected the Researcher role. The group difference was not statistically detectable (Mann–Whitney U=400.5U=400.5 , p=.38p=.38 ); the split is shown for descriptive comparison. A diverging stacked bar chart showing the distribution of trust ratings for three groups: all participants, researchers, and non-researchers. Each bar is centred on the neutral rating and shows the percentage of participants at each point of a five-point trust scale.
More in this topic

Systematic Review Automation

See all 18 papers

Explore similar work

CardsList
Jul 27, 2026

Preliminary Guidelines for Using and Evaluating GenAI Tools to Support Systematic Literature Reviews

Context: Generative AI (GenAI) and Large Language Models (LLMs) are increasingly used for academic tasks in software engineering and beyond, including systematic literature reviews (SLRs). However, while capable of summarizing text, there is no guarantee they can meet the rigour, reliability, and transparency that SLRs require. Objectives: To support researchers intending to conduct SLRs using GenAI or those conducting empirical studies evaluating how well GenAI supports SLR tasks. Methods: First, we conducted a rapid review to identify studies that propose guidelines for evaluating and using GenAI and LLMs to support SLRs. Second, we drew on thought experiments, relevant guidance from the literature, and our own experience conducting SLRs and evaluating tools to develop recommendations for how to use and assess GenAI in the context of SLRs. Results: We discuss the problems researchers face when evaluating GenAI for SLRs. We identify and explain process issues to consider when planning, conducting, and reporting both SLRs using GenAI and evaluations of GenAI tools. Finally, we summarize our results as a set of process recommendations, which we name GUEST (GenAI Use and Evaluation in SLR Tasks). Conclusion: We argue that GenAI requires human oversight and is not currently capable of unsupervised systematic studies. However, it offers the prospect of cost-effective assistance for some repetitive tasks and for additional validation of some complex tasks. Our GUEST recommendations should help software engineering researchers both to conduct and report trustworthy SLRs using GenAI and to provide rigorous independent evaluation studies.

Barbara Kitchenham, Sebastián Pizard, Lech Madeyski +3

Keele University, United Kingdom · Universidad de la República, Uruguay · Wrocław University of Science and Technology, Poland +3

LLM EvaluationSystematic Review AutomationHuman-in-the-Loop EvaluationGenerative AI Evaluation
AskPDF
Mar 20, 2026

Evaluating AI-based Scientific Knowledge Synthesis with Epidemiological Systematic Reviews

Systematic literature reviews (SLRs) are a demanding and high-stakes form of scientific knowledge synthesis that remains underspecified as an evaluation setting for large language models (LLMs). We introduce AgentSLR, a large-scale evaluation harness comprising an SLR automation workflow and an expert annotated dataset covering 16,248 articles, designed to test LLM capabilities across the stages of SLRs in epidemiology. Reference annotations were derived from peer-reviewed studies on WHO priority pathogens and produced by domain experts. The harness evaluates each review stage as a separate unit with dedicated metrics enabling targeted failure analysis. We evaluated five frontier reasoning models and found that no single model dominated across all tasks, showing sub-task specialisation often hidden by aggregate benchmarks. Structured data extraction is a major bottleneck, with no model exceeding an average field-level F1 of 0.67. Estimated costs vary substantially, by up to 96 times across evaluated models. Documented failure modes suggest that the evaluated models are not yet reliable enough for unsupervised deployment in epidemiology, where findings can inform public policy.

Shreyansh Padarha, Ryan Othniel Kearns, Tristan Naidoo +13

University of Oxford · Imperial College London · University of Nottingham +2

Systematic Review AutomationLLM EvaluationScientific Workflow AutomationLLM Information Extraction
AskPDF
Sep 10, 2026

PRISMA-LLM: An Empirical Reporting Framework for AI-Assisted Systematic Reviews

Large language models (LLMs) and AI-enabled software increasingly participate in systematic-review decisions, yet the information needed to audit these workflows is reported inconsistently. We analyze SciLitBench, a corpus of 888 review-automation papers with 14,726 annotations, to characterize changes in methods, review-stage use, evaluation and reported limitations. Automation has shifted toward LLM- and software-facing workflows, including stages that can alter the evidence base. Since 2023, 38.0% of software/product papers reported no evaluation, compared with 9.3% of LLM papers. Reporting coverage increased with LLM workflow complexity, yet 52% of positive-only LLM evaluations still reported an unmet reliability or performance requirement. From these patterns, we introduce PRISMA-LLM, an empirically grounded framework separating implementation disclosure from consequence-sensitive evaluation and limitation reporting.

Miguel Zabaleta, Baihan Lin

Department of AI and Human Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, USA · Department of Neuroscience, Icahn School of Medicine at Mount Sinai, New York, NY, USA

LLM AuditingSystematic Review AutomationAI-Assisted Scientific ResearchLLM ReliabilityAutomated Evaluation
AskPDF