It is the week before your literature review is due, and a chatbot has just handed you ten perfectly formatted references: real-sounding authors, a plausible journal, a tidy DOI on the end. You paste them into your bibliography and move on. The problem is that some of those papers were never written. The model produced the shape of a citation, the way it produces the shape of a sentence, and it cannot tell the difference between a study that exists and one that merely sounds like it should.
This is the trap at the centre of using AI for research, and it is entirely avoidable. There is now a small class of tools built specifically to search the actual scientific literature, ground their answers in papers you can open, and show you the sentence a claim came from. Used well, they turn a fortnight of database wrangling into an afternoon. Used carelessly, or confused with a general chatbot, they are a fast route to an academic misconduct panel. The difference is a workflow, not a secret.
A chatbot does not look things up and then tell you. It predicts what a plausible answer looks like. Sometimes that plausible answer is true.
Why the chatbot lies so wellThe fabricated-citation problem
Start with the failure mode, because it explains everything that follows. A general model such as ChatGPT, Gemini or a plain Claude chat is a next-word predictor. Ask it for sources and it generates text that resembles a reference list, assembled from patterns in its training data rather than retrieved from a database. The result is what researchers politely call a hallucinated reference: a citation that looks impeccable and points at nothing.
The rate is not trivial. A 2025 Deakin University study that checked references generated by GPT-4o found that roughly one in five citations were entirely fabricated, and more than half were either fake or carried factual errors. Earlier work published in Scientific Reports documented the same behaviour: invented titles, real authors bolted to papers they never wrote, DOIs formatted flawlessly and leading nowhere. The citations are convincing precisely because sounding right is the only thing the model is optimised to do.
Never cite a source you have not opened and read yourself. If an AI mentions a paper, treat that as a lead, not a fact. Find it on the publisher's site, Google Scholar or your library, confirm it exists, confirm it says what the AI claims, then cite the paper. If you cannot find it, it very likely does not exist, and a fabricated citation in your bibliography is misconduct whether you knew or not.
Tools that cite real papersThe discovery engines
The fix is to use tools that retrieve first and write second. Instead of inventing text, they search an index of genuine publications, then summarise what they actually found, with a link back to each one.
- Elicit is the closest thing to an AI research assistant for a literature review. It searches across roughly 125 million papers, finds relevant work even without an exact keyword match, and its signature trick is extraction: it pulls sample sizes, methods and outcomes into a table, one row per paper, so you can compare twenty studies at a glance. Every extracted figure shows the supporting quote from the source.
- Consensus answers a specific question by reading across the literature. Ask "does spaced repetition improve long-term recall" and it returns a synthesised answer, the papers behind it, and a "consensus meter" showing how much the studies actually agree. It searches over 200 million papers and is built for evidence, not chat.
- Semantic Scholar is the free, no-frills backbone: a scholarly search engine from the Allen Institute for AI covering hundreds of millions of papers, with citation graphs and AI-generated summaries. It is the reliable place to confirm a paper exists and see who cited it.
Grounding on your own readingNotebookLM and Claude Science
A second category does something subtly different. Rather than search the whole internet, these tools answer only from the documents you give them, which is exactly what you want once you have gathered your papers and need to interrogate them.
Google NotebookLM lets you upload up to fifty sources, PDFs, your own notes, lecture slides, and then ask questions across them. Because it is grounded in your uploads, it will not wander off into invented facts, and every answer carries inline citations you can click to jump to the exact passage. It is superb for "what did these six papers say about my variable" and for turning a stack of reading into a revision summary. One honest limit: it points you to the source, but you still write the page-level reference yourself.
At the heavier end, Anthropic launched Claude Science at the end of June 2026, an AI workbench that connects Claude (Opus 4.8 included) to more than 60 scientific databases such as UniProt, PDB and ChEMBL. A coordinating agent parcels work out to specialists, and, notably, a separate reviewer agent checks every citation and calculation as it goes. It is aimed at working scientists in genomics, chemistry and structural biology rather than a first-year essay, but it signals the direction of travel: retrieval and verification built in, not bolted on.
| Tool | Best for | Free access? |
|---|---|---|
| Elicit | Finding papers, extracting data into comparison tables | Free tier, then paid credits |
| Consensus | Evidence-based answers to a specific question | Free tier, then ~£8/mo |
| Semantic Scholar | Confirming a paper exists, citation graphs | Fully free |
| NotebookLM | Grounded answers from papers you upload | Free |
| Claude Science | Deep science across 60+ databases | Paid subscription |
A workflow that keeps you honestDiscover, triage, read, cite
The tools only help if you keep them in their lane. A sane research loop looks like this, and the order matters:
- Discover. Use Elicit or Consensus to surface candidate papers and get the lay of the land on your question. Treat the summaries as a map, not the territory.
- Triage. Skim the AI summaries to decide which handful of papers are actually worth your time. This is where the tools save you most: killing the ten irrelevant results before you open anything.
- Read the real paper. Open the source itself. Check that it exists, that it says what the summary claimed, and that the method and sample actually support the point you want to make.
- Cite the paper, not the AI. Your reference is to the study you read, in your own words, with your own critical read of it. The AI was scaffolding; it does not appear in your bibliography as a source of facts.
Do it in that order and the AI never touches the part that has to be trustworthy. Skip to citing before reading, and you are one hallucinated DOI away from trouble.
By the numbersWhy verification is not optional
Read the rules firstWhat your university actually requires
None of this is a licence to hand in AI-written work. UK policy is fragmented but converging, and the Russell Group principles, adopted across its 24 universities, are the clearest guide. The starting assumption in most schemes is blunt: unless an assessment explicitly permits it, generative AI is not allowed, and its output must be treated like any other person's work, acknowledged and cited, never passed off as your own.
In practice that means three things. Check the rubric for the specific assignment, because permission varies by module. Where AI use is allowed, declare it as your institution requires, usually a short statement of which tool you used and how. And understand that two things are always misconduct regardless of policy: submitting AI-generated text as your own writing, and citing sources you never verified. A fabricated reference is not a grey area. It is a fabrication.
The honest summary is cheering, not scary. These tools are genuinely good at the tedious 80% of a literature review: casting a wide net, summarising abstracts, organising what you find. They are not a shortcut through the 20% that is actually your degree: reading critically, thinking, and writing it up in your own voice. Keep AI on the discovery side of that line, verify every source with your own eyes, and you get the speed without the risk. Cross it, and the tool that was meant to save your dissertation is the thing that sinks it.
Get the next one in your inbox
One AI tool, one prompt, three quick wins, every week. Free, and under 3 minutes to read.
Subscribe Free →