How to Prevent AI Hallucinations in Legal Research and Drafting

9 September, 2026

AI has become part of daily practice for attorneys, litigators, associates, and paralegals who need to move faster through research and drafting. But alongside that adoption has come a well-publicized problem: AI hallucinations, where a tool confidently produces a citation, quote, or holding that si...

The Law of the Hallucination

4 September, 2026

A technology arrives that the profession does not know how to think about, and the response follows a reliable sequence. First the anecdotes, then the sanctions, then the committees, and, at last, the question of whether a new body of law is required. Hallucinated citations have now carried us to th...

What is Legal AI?

3 September, 2026

If a partner asked you right now what's happening on all 200 active matters, how long would it take to answer honestly? For most firms, the task involves someone pulling up dozens of different files, texting a paralegal, and hoping nothing slipped through since Friday.  Legal AI offers a new wa...

Solving Hallucinations with LOIS

1 September, 2026

Courts across the country are increasingly sanctioning attorneys whose filings cite cases that do not exist, quote language never written, or misconstrue holdings. Filevine’s Legal Operating Intelligence System (“LOIS”) catches those errors at the draft stage.  Filevine’s internal legal researc...

What Is the Best AI for Lawyers?

25 August, 2026

It’s a big question, and the answer depends on your firm. Attorneys, litigators, associates, and paralegals each use AI differently. A litigator preparing for trial has different needs than a transactional attorney closing deals, and both have different needs than the knowledge management director e...

Finding Ground Truth: How We Evaluate Legal AI at Filevine

10 August, 2026

At ML Prague, I gave a talk on a problem that doesn't get enough airtime: how do you actually know whether a legal AI system is any good? Much of the energy in our field right now goes into the generation side - bigger models, smarter agents, and more capable tool use. That's fair, and it matters. B...