Reliability & accuracy
Is AI legal research accurate for Australian law?
General-purpose AI chatbots are unreliable for Australian legal research — they can invent cases, statutes and citations that look real but do not exist. Purpose-built legal AI trained on a maintained Australian and New Zealand corpus is far more accurate, but accuracy still depends on two things: whether every answer carries a verifiable source citation, and whether the system is built to decline rather than guess when no authority exists. A lawyer must verify each result against the primary source.
Why general chatbots get Australian law wrong
Consumer chatbots are trained on broad internet text, not a curated, current Australian legal database. They have no reliable model of jurisdiction, no guaranteed coverage of all eight states and territories plus the Commonwealth, and a training cut-off that leaves recent decisions and amendments out.
Worse, they are built to produce a fluent answer even when they have no source — which is how lawyers end up with confident citations to cases that were never decided. The fluency is the trap: the output reads like authority but is not anchored to one.
What makes legal AI accurate enough to use
Accuracy comes from a maintained, current corpus of Australian and New Zealand law — all states and territories, federal law, and New Zealand where you need it — kept up to date rather than frozen at a training cut-off.
Just as important is a source citation on every result, so you can click through and confirm the authority, and a design that refuses to answer rather than fabricate when no authority exists. Plain-English querying (no Boolean syntax) helps, but it is the citation and the refusal behaviour that make the output safe to build on.
How to verify AI legal research
Treat every AI answer as a lead, not a conclusion. Open the cited authority, confirm it exists, check it is the right jurisdiction and still good law, and read the passage yourself before relying on it.
Verification is the lawyer’s responsibility and always will be — the value of good legal AI is that it does the searching and surfaces the citation so verification takes minutes, not hours.
Where Quillio sits
Quillio is built for Australian and New Zealand law, with a maintained current corpus across all eight states and territories, the Commonwealth courts, and New Zealand. It returns a source citation on every research result and is built to refuse rather than fabricate when no authority exists — so you can verify every answer rather than trust it blind.
Frequently asked questions
Can ChatGPT do Australian legal research?
It can help explain general concepts, but it is not safe for citations or authorities — it has no dedicated, current Australian legal corpus and can fabricate cases. Never rely on a general chatbot’s legal citations without verifying each against the primary source.
Does AI cover all Australian states?
Purpose-built legal AI can, but coverage varies by vendor. Confirm the tool maintains a current corpus across all eight states and territories and federal law (and New Zealand if you practise trans-Tasman) before relying on it.
Can I cite AI in a court document?
You cite the underlying authority, not the AI. Always open and read the primary source, confirm it exists and is current, and cite that — courts have sanctioned lawyers who filed AI-generated citations without checking them.
See how Quillio handles this in practice
AI built for Australian and New Zealand law — a citation on every answer, client content stored in Australia, and a free trial so you can test it on your own files.