The AI Learning Hub Journal

Retrieval Helps. It Does Not Cure.

What retrieval fixes, and what it leaves behindeducational orientation only — not legal advice1The questiona research question posedin the words of the matter2Retrieve real sourcesa genuine collection is searchedand passages are returned3Answer, groundedthe model writes from what cameback, and points at itWHAT THIS GENUINELY FIXESThe fabricated source is largely designed out — what is cited now exists, and the link back can be followed to a real documentWHAT IT DOES NOT FIX — ALL FOUR SURVIVE PERFECT RETRIEVALMischaracterisedThe source is real. The account of itis not. Reasoning is compressed intoa summary that quietly overstates it.the source is real throughoutCited past its holdingReal source, real passage, stretchedto support a proposition it neverdecided — the commonest failure.the source is real throughoutControlling authority missedRetrieval returns what matches thewords used. What governs may bephrased nothing like the question.the source is real throughoutSuperseded and still citedThe document exists and is no longergood — retrieval can surface thingslater material has already displaced.the source is real throughoutRetrieval reduces risk. Verification remains mandatory.Open the source, read the passage, confirm it says what the answer says it says, and check it is still good — every timeA grounded answer is easier to check, which is not the same as already checked
Retrieval removes the invented source and leaves every other failure untouched — grounding changes the odds, not the duty to read what is cited

How Retrieval-Backed Research Changes the Picture

Research tools built on retrieval work differently from a bare chatbot. Instead of generating an answer from model weights alone, they search an actual corpus of primary and secondary sources, retrieve relevant documents, and instruct the model to answer using only those documents, usually with links back to what was retrieved. This is a genuine improvement and it substantially reduces the wholly-invented-case failure, because the citations come from a real index rather than from the model's learned patterns. If a firm is going to use AI for legal research at all, a properly grounded, source-linked tool is a materially safer starting point than a general assistant. That is a real distinction and worth insisting on in procurement.

  • Grounded tools search a real corpus and cite what they retrieved, rather than generating from weights
  • This substantially reduces wholly-invented citations — the citation comes from a real index
  • A source-linked, grounded tool is materially safer than a general assistant for research
  • Insist on visible source links in procurement; a tool without them is not grounded in any useful sense

The Failure Modes Retrieval Does Not Remove

Grounding narrows the failure surface without closing it. The model still summarises what was retrieved and can misstate a holding, overstate how squarely a case supports a point, or lose a crucial qualification. Retrieval can surface a real case that is genuinely on point but has since been overruled, distinguished, or superseded by statute, and currency-checking is a separate function that not every tool performs. Coverage gaps are invisible: if the corpus lacks a jurisdiction or a court level, the tool answers confidently from what it does have. Chunked retrieval can sever a passage from a qualification appearing elsewhere in the judgment. And a generated synthesis can drift from the sources beneath it while still displaying them as citations.

  • Misdescription of retrieved authority survives grounding entirely — the summary is still generated
  • Overruled, distinguished, or superseded authority can be retrieved and cited as current
  • Corpus coverage gaps are silent; the tool answers from what it has without signalling what it lacks
  • Chunking can separate a passage from the qualification that changes its meaning
  • Measured, not asserted: a Stanford RegLab study of leading AI legal research tools (Journal of Empirical Legal Studies, 2025) found hallucination rates from roughly one in six to one in three of the queries tested

Reading a Grounded Answer Correctly

The right mental model for a grounded research tool is a fast, tireless, and occasionally careless researcher who always hands you the documents. The value is in the documents. The prose summary is a navigational aid — useful for deciding what to read, never a substitute for reading it. In practice this means clicking through to every source before relying on the answer, reading enough of each source to confirm it says what the summary claims, and checking currency independently. It also means noticing when a tool returns a confident answer with thin or tangential sources, which is a signal that the corpus did not contain a good answer and the model synthesised around the gap.

  • The retrieved documents are the product; the summary is a navigational aid to them
  • Click through to every source and read enough to confirm the characterisation holds
  • Check currency separately unless the tool explicitly performs and displays that function
  • A confident answer resting on thin or tangential sources means the corpus fell short

Prefer slides, quizzes, and saved progress? Read this lesson in the library — free, no sign-up.