How to Check Your Students' Citations for AI Hallucinations

Why this is a different problem than plagiarism

A similarity checker compares a student's text against a corpus of existing writing. It's built to answer "did this come from somewhere else?" It was never built to answer a much narrower, newer question: "does the source cited on page 4 actually exist, and does it say what the student claims?"

That second question matters more than it used to, because LLMs don't fail at citations the way a student copying from Wikipedia fails. An LLM asked to draft a reference list will produce entries that are stylistically perfect — correct APA or MLA formatting, plausible author names, a journal that sounds real — while citing a paper that was never published, or attaching the wrong year and publisher to a real one. None of that trips a plagiarism check, because none of it is copied from anywhere. It's fabricated from the model's sense of what a citation should look like.

What to actually check for

There are three distinct failure modes worth looking for, and they call for different responses:

• Hallucinated: the citation doesn't exist in any indexed academic database. No DOI, no matching title, nothing. This is the clearest sign a source was never read — possibly never checked by the student at all.
• Mismatch: something real is cited, but a detail is wrong — the year, the author list, the journal, the DOI. Sometimes this is sloppy manual transcription. Sometimes it's an LLM blending two real papers into one citation.
• Verified: the source exists and the metadata lines up. No further action needed on that entry.

The point isn't to accuse every student with a hallucinated citation of academic dishonesty — sometimes it's a rough draft, a citation manager error, or a source they meant to double-check and forgot to. But you can't have that conversation at all if you don't know which citations to look at first.

Step-by-step: checking a stack of papers at once

1. Collect the papers as PDFs. AccuraCite's Bulk Verification plan accepts up to 30 PDFs in a single scan — a full section's worth of essays or a batch of thesis chapters in one job, instead of one paper at a time.
2. Drop them into a bulk scan. From your workspace, open the Bulk Verification tab and upload the set. AccuraCite's parser extracts each paper's reference list automatically, regardless of which citation style the student used.
3. Let it cross-check against real sources. Every extracted citation is queried against six independent academic databases at once — OpenAlex, Crossref, Semantic Scholar, PubMed, DBLP, and arXiv — and a consensus vote decides the result, so a single noisy or wrong database entry doesn't produce a false "verified." Read more on the How It Works page.
4. Read the per-file breakdown, not just a score. Each file in the run shows a verified/total ratio and expands into the individual citations, so you can go straight to the paper with 6 hallucinated sources out of 12 instead of skimming every bibliography by hand.
5. Follow up on what's flagged, not what's clean. A hallucinated or mismatched citation is a prompt to ask the student where the source actually came from — not an automatic verdict. Treat it the way you'd treat a plagiarism-checker flag: a lead, not a conclusion.

What this doesn't replace

This isn't a substitute for a plagiarism/similarity checker, and it isn't a grading tool. It answers one specific question — "is this reference list real?" — that similarity checking was never designed to answer. Most instructors get the most value running both: a similarity check for copied text, and a citation check for fabricated sources, since an LLM-assisted paper can pass the first and fail the second cleanly.

It's also not a guarantee that a "verified" citation was actually read or used correctly — only that the source exists and the metadata matches. A student can cite a real paper about something the paper doesn't actually say. AccuraCite confirms the reference is real; it doesn't (yet) confirm the argument built on top of it is honest.

If you're reviewing a submitted manuscript instead of grading student work, see how to check citations as a peer reviewer.

How to raise a flagged citation with a student

The framing matters. "This citation doesn't check out — walk me through where you found it" opens a conversation. "You fabricated a source" starts one that assumes the answer before you've heard it. Most instructors find the actual explanations fall into a few buckets: a citation manager dropped or garbled a field, the student used an LLM to help draft a literature review and never went back to confirm each reference, or — less often — the source was invented outright because a real one supporting the claim couldn't be found in time. Only the last of those is a straightforward integrity violation; the first two are closer to a sourcing error, and worth treating as a teachable moment about verifying AI-assisted work rather than an automatic academic-dishonesty case.

A hallucinated citation is also not, by itself, proof the surrounding prose was AI-written — a student can write every word of an essay themselves and still cite a source an LLM handed them without checking it. Keep the two questions separate: whether the citations are real, and whether the writing is the student's own.

Building this into your course policy

If you're going to check citations this way regularly, it's worth stating so upfront in your syllabus or assignment instructions, the same way you'd disclose the use of a plagiarism checker. Being explicit that references will be verified against real academic databases, before the fact rather than after a stack of graded papers turns up problems, tends to reduce how often you see fabricated citations in the first place — most students who'd otherwise skip verifying an AI-drafted reference list will do it themselves if they know it's part of what's being graded. It also gives you clearer footing if a check does turn up a problem: the expectation was disclosed, not sprung on them after the fact.

FAQ

Do I need every student's paper to be a clean PDF? Yes — the bulk scanner parses PDFs directly, extracting the reference list regardless of citation style (APA, MLA, Chicago, IEEE, and others are auto-detected).

What if a citation is real but formatted incorrectly? That's flagged as a mismatch, not a hallucination — the tool distinguishes "this doesn't exist" from "this exists but something's off," so you're not treating a typo the same as a fabricated source.

Can I check papers one at a time instead of in bulk? Yes — the Pro plan supports single-PDF scans, and the free AI Citation Checker works from pasted citation text if you just need to spot-check one paper. Bulk scanning (up to 30 PDFs per job) is built for exactly this use case — checking a whole class set or stack of submissions at once — and is available on the Bulk Verification plan or the 7-Day Bulk Pass for a shorter grading window.

Does this tell me if a student used AI to write the paper? No — it tells you whether the citations in the paper are real. That's a narrower, more concrete signal than AI-writing detection, and it doesn't rely on guessing at writing style, which is part of why it's harder to fool: a citation either exists in the indexed literature or it doesn't.

Should I tell students in advance that I check citations this way? Yes, generally — stating it in your syllabus or assignment brief tends to reduce how often fabricated citations show up in the first place, and gives you clearer footing if a check does turn something up, since the expectation was disclosed rather than sprung on them after grading.

What about a group project where only one member drafted the bibliography? Treat it the same way you'd treat a group project citation issue found any other way: raise it with the group, since a shared submission carries shared responsibility for the reference list, but let the conversation about who actually drafted it happen before assigning individual consequences.