“I had 47 papers and zero idea where to start. uploaded everything and had a 3,000-word draft by that evening. not perfect but way better than staring at a blank page for another week”
Maria K.
Undergraduate, Neuroscience
Upload your sources. We organise the literature around your research question, with real citations from YOUR papers. In hours, not weeks.
Free to try · No credit card required
Not all AI writing tools are built for academic work.
| Feature | Litrevu | ChatGPT | Jenni AI | Manual |
|---|---|---|---|---|
| Cites your uploaded papers | Yes | Partial | From library | Yes |
| No hallucinated references | Yes | No | Partial | Yes |
| Structured report (8 sections) | Built-in | Manual prompting | Partial | Yes |
| Time to structured synthesis | 2–4 hrs | Hours of prompting | Hours of editing | 40–80 hrs |
| Auto-formatted citations | All major styles | Inconsistent | Partial | Manual |
| Pricing | From $8.49 once | Free / $20 mo | $12–29/mo | Your time |
Cites your uploaded papers
No hallucinated references
Structured report (8 sections)
Time to structured synthesis
Auto-formatted citations
Pricing
From undergrads to PhD candidates, across every discipline.
“I had 47 papers and zero idea where to start. uploaded everything and had a 3,000-word draft by that evening. not perfect but way better than staring at a blank page for another week”
Maria K.
Undergraduate, Neuroscience
“my thesis had 89 references and every single citation actually matched the pdfs I uploaded. thats what got me to buy the full thing”
James L.
Masters student, Psychology
“I was so stuck on my lit review I almost asked for an extension. this gave me a structure to work from and I just edited from there. handed in on time with 2 days to spare”
Tom R.
Undergraduate, Economics
“turned a 2-week lit review into a weekend job. uploaded 35 papers, got a solid synthesis with proper citations as a starting point. worth every cent honestly”
Aisha M.
Honours student, Public Health
“usually AI stuff sounds robotic and you spend ages fixing it. this actually read like something I would write? didn’t have to change that much”
Daniel S.
Masters student, Philosophy
“biggest timesaver was not having to reread all my sources. it pulls out the relevant bits and cites them properly. I just checked and tweaked”
Hannah W.
Undergraduate, Education
Add your sources (upload PDFs or pull papers from OpenAlex) and Litrevu reads and synthesizes them into structured notes with real citations. You guide the topic and research question, and the AI extracts key findings from your sources for you to review, revise, and rewrite in your own voice. 800 words free, no credit card required. Read more about AI research assistance for literature reviews.
Most literature reviews can be synthesized in under two hours. A traditional lit review takes 40\u201380 hours of reading. Litrevu reads your uploaded papers and extracts a structured synthesis with citations in minutes per section. Your starting point to review and revise. See our step-by-step literature review guide.
No. Every citation comes from your sources. Litrevu never invents references. It uses retrieval-augmented generation (RAG) to pull content exclusively from your sources, so every reference is real and verifiable.
APA, MLA, Chicago, Harvard, Vancouver, and IEEE. You can switch between citation styles instantly after generation. Most students use APA or Harvard formatting. Learn how to cite sources in a research paper.
Not at all. Litrevu synthesizes your sources for every section of a research paper: Introduction, Literature Review, Methodology, Results, Discussion, Conclusion, Abstract, and Title. You review, revise, and rewrite each section. Most students start with the free Introduction synthesis, then upgrade for the rest. See the full research paper structure.
Start free with 800 words (enough for your Introduction). Paid plans are a one-time purchase, not a subscription: Starter at $8.49 for 7,500 words, Scholar at $29.99 for 50,000 words, and Platinum at $99.99 for 250,000 words.
Find relevant papers on your topic through Litrevu, or upload your own. Free accounts support up to 10 sources, Starter 30, Scholar 100, and Platinum up to 5,000. The more sources, the richer your citations.
Litrevu produces a structured synthesis that you must review, revise, and rewrite in your own voice before submitting. Because the output is grounded in YOUR uploaded sources (not generic text), it reads more like genuine academic content than typical AI output. That said, always revise thoroughly. The more you rework the synthesis, the more it reflects your thinking. Read our take on AI detection and process-based evaluation.
Buy once. No subscriptions, no recurring charges.
800 words to try your first section
7,500 words • Perfect for a single assignment
50,000 words • Enough for a full thesis
250,000 words • For labs and power users
30-day money-back guarantee · Secure payment
800 words free. No credit card, no commitment.
Try it free256-bit SSL · Your papers are never shared · Not used for AI training · Delete anytime
Upload your papers, answer a few questions, and get a structured synthesis with real citations.
Global Warming of 1.5°C: An IPCC Special Report on the Impacts of Climate Change
Masson-Delmotte, V. et al., 2018
Attribution of Extreme Weather Events in the Context of Climate Change
Stott, P. et al., 2016
Increases in the Frequency of Warm-Season Heavy Precipitation Since 1950
Fischer, E. et al., 2015
Human Contribution to the European Heatwave of 2003
Stott, P. et al., 2004
Anthropogenic Influence on Long Return Period Daily Temperature Extremes at Regional Scales
Christidis, N. et al., 2015
The Role of Sea Surface Temperature Forcing in the Life Cycle of Mediterranean Cyclones
Miglietta, M. et al., 2023
Clausius-Clapeyron Scaling of Extreme Hourly Convective Precipitation
Lenderink, G. et al., 2017
Rapid Attribution Analysis of the Extraordinary Heatwave on the Pacific Coast in June 2021
Philip, S. et al., 2022
Atmospheric River Tracking Method Intercomparison Project
Rutz, J. et al., 2019
Future Changes in Atmospheric Rivers and Extreme Precipitation in Norway
Hegdahl, T. et al., 2020
A Review of the Relationships Between Extreme Weather Events and Climate Change
Trenberth, K. et al., 2015
Global Increase in Record-Breaking Monthly-Mean Temperatures
Coumou, D. et al., 2013
The Intensification of Short-Duration Rainfall Extremes With Warming
Fowler, H. et al., 2021
Quantifying the Influence of Climate Change on Tornado Environments
Diffenbaugh, N. et al., 2013
Tropical Cyclone Rainfall Changes in a Warming Climate
Knutson, T. et al., 2020
Hover any citation to see the source · Switch styles above
The scientific understanding of how anthropogenic climate change intensifies extreme weather events has evolved rapidly over the past two decades, drawing on advances in observational climatology, attribution science, and climate modelling. The IPCC Special Report on Global Warming of 1.5°C established that global mean surface temperature had risen by approximately 1.1°C above pre-industrial levels, with the rate of warming accelerating markedly since the 1970s [1]. This foundational assessment has framed subsequent research by quantifying the baseline shift against which extreme event trends must be evaluated. Stott, Christidis, and Otto (2016) extended this framework by developing probabilistic event attribution methods that enable researchers to isolate the anthropogenic signal in individual extreme weather events [2], a methodological advance that has transformed the field from correlational observation to causal inference.
Observational evidence consistently demonstrates that heavy precipitation events have intensified in tandem with global warming. Fischer and Knutti (2015) analysed long-term precipitation records across the Northern Hemisphere and found that heavy precipitation events increased by 18–40% in intensity since 1950 [3], with the strongest trends in regions experiencing the greatest surface warming. These findings align with the thermodynamic expectation that a warmer atmosphere holds more moisture. However, the relationship between warming and precipitation extremes is not purely thermodynamic. The pioneering attribution study by Stott, Stone, and Allen (2004) on the 2003 European heatwave demonstrated that anthropogenic emissions had at least doubled the probability of that event [4], establishing that dynamic circulation changes also play a critical role in shaping extreme event likelihood. Christidis, Jones, and Stott (2015) subsequently showed that regional temperature extremes now exceed natural variability by three to five standard deviations in many areas [5], providing further evidence that the observed intensification cannot be explained by internal climate variability alone.
At the mesoscale, the interaction between warming ocean surfaces and atmospheric dynamics creates additional amplification pathways for extreme weather. Miglietta, Laviola, and Levizzani (2023) demonstrated that sea surface temperature anomalies amplify Mediterranean cyclone intensity by 20–35% through enhanced latent heat flux [6], highlighting the role of ocean-atmosphere coupling in regional extreme event intensification. The Clausius-Clapeyron relation provides a theoretical anchor for understanding precipitation scaling, with Lenderink and Fowler (2017) confirming that extreme hourly precipitation increases at approximately 7% per degree of warming [7]. This scaling relationship has proven remarkably robust across different geographic regions and precipitation types, though notable exceptions exist for convective extremes.
The attribution of individual extreme events has yielded some of the most compelling evidence linking climate change to weather disasters. Philip et al. (2022) conducted a rapid attribution analysis of the June 2021 Pacific Northwest heatwave and concluded that the event was virtually impossible without anthropogenic climate change [8]. This finding was particularly significant because the heatwave shattered existing temperature records by 4–5°C, suggesting that the tails of the temperature distribution may be shifting faster than the mean. In parallel, research on atmospheric rivers has revealed their outsized role in driving extreme precipitation, with Rutz et al. (2019) documenting that these narrow corridors of moisture transport account for 40–75% of extreme precipitation events on western coastlines [9]. Hegdahl, Engeland, and Muthanna (2020) extended this work by projecting that atmospheric river frequency over Norway may increase by 30–50% under high-emission scenarios by 2100 [10].
Several cross-cutting themes emerge from the synthesis of this literature. Trenberth, Fasullo, and Shepherd (2015) articulated the fundamental hydrological principle that a warmer atmosphere holds approximately 7% more moisture per degree Celsius of warming [11], which has become the organising framework for understanding precipitation changes across scales. The statistical evidence is equally striking: Coumou, Robinson, and Rahmstorf (2013) documented that monthly heat records occurred five times more frequently during 2000–2012 than expected under a stationary climate [12]. For convective precipitation, Fowler, Lenderink, and Prein (2021) showed that sub-hourly rainfall intensities may scale at two to three times the Clausius-Clapeyron rate [13], a super-scaling phenomenon with critical implications for urban flood risk. The influence of warming extends to severe convective environments, with Diffenbaugh, Scherer, and Trapp (2013) projecting a 20–45% increase in favourable severe thunderstorm conditions across the eastern United States by mid-century [14]. Finally, Knutson, Sirutis, and Zhao (2020) projected that tropical cyclone rainfall rates will increase by 10–15% in a 2°C warmer world [15], underscoring the global scope of precipitation intensification across storm types and geographic regions.
[1] V. Masson-Delmotte et al., "Global warming of 1.5°C: An IPCC special report," IPCC, 2018.
[2] P. Stott, N. Christidis, and F. Otto, "Attribution of extreme weather events in the context of climate change," WIREs Climate Change, vol. 7, no. 1, pp. 23-41, 2016.
[3] E. Fischer and R. Knutti, "Anthropogenic contribution to global occurrence of heavy-precipitation and high-temperature extremes," Nature Climate Change, vol. 5, pp. 560-564, 2015.
[4] P. Stott, D. Stone, and M. Allen, "Human contribution to the European heatwave of 2003," Nature, vol. 432, pp. 610-614, 2004.
[5] N. Christidis, G. Jones, and P. Stott, "Anthropogenic influence on daily temperature extremes at regional scales," J. Climate, vol. 28, pp. 9363-9380, 2015.
[6] M. Miglietta, S. Laviola, and V. Levizzani, "Sea surface temperature forcing in Mediterranean cyclone life cycles," Atmospheric Research, vol. 281, p. 106472, 2023.
[7] G. Lenderink and H. Fowler, "Clausius-Clapeyron scaling of extreme hourly convective precipitation," J. Hydrometeorology, vol. 18, pp. 1917-1932, 2017.
[8] S. Philip et al., "Rapid attribution analysis of the extraordinary heatwave on the Pacific coast," Earth Syst. Dynam., vol. 13, pp. 1689-1713, 2022.
[9] J. Rutz et al., "The Atmospheric River Tracking Method Intercomparison Project," Geosci. Model Dev., vol. 12, pp. 1541-1563, 2019.
[10] T. Hegdahl, K. Engeland, and T. Muthanna, "Future changes in atmospheric rivers and extreme precipitation in Norway," J. Hydrometeorology, vol. 21, pp. 1613-1626, 2020.
[11] K. Trenberth, J. Fasullo, and T. Shepherd, "Attribution of climate extreme events," Nature Climate Change, vol. 5, pp. 725-730, 2015.
[12] D. Coumou, A. Robinson, and S. Rahmstorf, "Global increase in record-breaking monthly-mean temperatures," Climatic Change, vol. 118, pp. 771-782, 2013.
[13] H. Fowler, G. Lenderink, and A. Prein, "Intensification of short-duration rainfall extremes and implications for flood risk," Nature Rev. Earth Environ., vol. 2, pp. 107-122, 2021.
[14] N. Diffenbaugh, M. Scherer, and R. Trapp, "Robust increases in severe thunderstorm environments in response to greenhouse forcing," Proc. Natl. Acad. Sci., vol. 110, pp. 16361-16366, 2013.
[15] T. Knutson, J. Sirutis, and M. Zhao, "Global projections of intense tropical cyclone activity for the late twenty-first century," J. Climate, vol. 33, pp. 4905-4925, 2020.
APA, Harvard, IEEE, MLA, Chicago, Vancouver.
Theoretical Framework
Sweller’s cognitive load theory posits that instructional design must account for the limited capacity of working memory during knowledge acquisition Sweller, 1988Cognitive Load During Problem Solving: Effects on LearningSweller, J. (1988)Key insightEstablishes that worked examples reduce extraneous load more effectively than conventional problem-solving for novices acquiring new schemas.Cited from your uploaded papers Sweller, 1994Cognitive Load Theory, Learning Difficulty, and Instructional DesignSweller, J. (1994)Key insightFrames instructional difficulty as element interactivity, separating intrinsic complexity from design-imposed extraneous load.Cited from your uploaded papers. Subsequent refinements by Paas and van Merriënboer distinguished between intrinsic, extraneous, and germane cognitive load, each of which interacts differently with learner expertise Paas & van Merriënboer, 1994Variability of Worked Examples and Transfer of Geometrical Problem-Solving SkillsPaas, F. & van Merriënboer, J. (1994)Key insightHigh-variability worked examples produced superior transfer to novel problems despite higher reported mental effort during practice.Cited from your uploaded papers. These distinctions have proven critical for designing multimedia environments that optimise information processing without overwhelming attentional resources Mayer, 2009Multimedia Learning (2nd ed.)Mayer, R. E. (2009)Key insightSynthesises twelve principles for multimedia instruction that minimise extraneous processing in dual-channel working memory.Cited from your uploaded papers Kalyuga, 2011Cognitive Load Theory: How Many Types of Load Does It Really Need?Kalyuga, S. (2011)Key insightArgues that the germane-vs-extraneous distinction is empirically unfalsifiable and proposes collapsing them into productive load.Cited from your uploaded papers.
Gaps in the Literature
Despite four decades of empirical work, the construct validity of germane load remains contested Kalyuga, 2011Cognitive Load Theory: How Many Types of Load Does It Really Need?Kalyuga, S. (2011)Key insightArgues that the germane-vs-extraneous distinction is empirically unfalsifiable and proposes collapsing them into productive load.Cited from your uploaded papers. Few studies have examined how individual differences in working memory capacity moderate the expertise-reversal effect outside laboratory settings Chen et al., 2017The Expertise Reversal Effect Is a Variant of the More General Element Interactivity EffectChen, O., Kalyuga, S. & Sweller, J. (2017)Key insightReframes the expertise reversal effect as a special case of element interactivity, predicting load shifts as prior knowledge grows.Cited from your uploaded papers. Longitudinal evidence connecting multimedia instruction to retention beyond the immediate post-test is also scarce, limiting claims about durable learning gains Sweller et al., 2019Cognitive Architecture and Instructional Design: 20 Year UpdateSweller, J., van Merriënboer, J. & Paas, F. (2019)Key insightTwenty-year review flags persistent shortage of longitudinal CLT studies measuring durable transfer beyond immediate post-tests.Cited from your uploaded papers.