The citator has two core features. One checks a filed or draft brief for hallucinated citations, altered quotations, and mischaracterized authority. The other checks whether a proposition is still good law by letting a lawyer highlight a specific passage in an opinion and find out whether later courts have undercut the holding expressed in the passage.<\/p>\n
Although Filevine had previously announced the citator in June<\/a> as part of its new LOIS Legal Research offering, which provides access to millions of opinions from U.S. federal and state courts, CEO Ryan Anderson, in a briefing this week, told me the company had not heavily promoted the citator until it believed the product was fully ready for customers to use.<\/p>\n The company had not previously announced the anti-hallucination tool, which is being released for the first time this week.<\/p>\n As Filevine described the citator in its June release: \u201cWhile legal verification tools rely on explicit citation relationships and apply treatment signals to entire opinions, LOIS Legal Research operates at the user-selected passage level.\u201d This enables legal professionals to verify the exact rule they plan to rely on in their argument.<\/p>\n I have previously written that developing a strong citator tool is the Holy Grail of a legal research platform<\/a>. Among companies to have tried it in recent years were vLex and Paxton<\/a>, Descrybe<\/a>, and Midpage<\/a>.<\/p>\n But it is not an easy task. In fact, in my briefing with Filevine this week, John Rizner<\/a>, the product manager who led the development of the citator, pointed out something that most law librarians will know but that may be news to almost everyone else, which is that the two citators lawyers have long considered to be the gold standard routinely disagree with each other about whether a case is still good law.<\/p>\n He pointed to a 2018 study in the Law Library Journal<\/a> by Paul Hellyer, a librarian at William & Mary Law School, who reviewed 357 citing relationships that at least one of Shepard\u2019s, KeyCite or BCite had labeled negative.<\/p>\n All three citators agreed that the treatment was negative only 53 times, meaning that in 85% of the relationships in Hellyer\u2019s sample, the three citators did not agree that a negative treatment had occurred.<\/p>\n Hellyer also examined whether the flags that did appear were correct. Counting relationships the citators omitted or mislabeled as positive or neutral, together with those labeled negative but incorrectly described, he found overall failure rates of 33% for Shepard\u2019s, 38% for KeyCite and 72% for BCite.<\/p>\n Rizner also cited a second line of research, from Susan Nevelow Mart, the former director of the law library at the University of Colorado, whose 2013 examinations of digest and citator results<\/a> found that the overlap between the Westlaw and Lexis citator systems on relevant results was small \u2013 only about a third.<\/p>\n As the abstract of Mart\u2019s article put it: \u201cNeither algorithm is doing a very good job of finding all the relevant results; the overlap between the two citator systems is not that large.\u201d<\/p>\n Ahead of our briefing, Rizner ran his own test. He pulled Freedom Mortgage Corp. v. Engel<\/em> on both platforms and filtered each down to negative treatment in reported opinions. Westlaw found 28 and Lexis found 13. The overlap between the two sets, by his count, was about 41%.<\/p>\n \u201cIf my law firm happens to have Lexis, I might be missing opinions because I don\u2019t have Westlaw, or vice versa,\u201d Rizner said.<\/p>\n What that means, Anderson said, is that even though the legacy citators have been best in class up until now, that does not mean that they do not make mistakes.<\/p>\n At this point, you may be thinking: \u201cSure, but what does this all have to do with Filevine, which is not a legal research platform?\u201d<\/p>\n In my opinion, it has everything to do with Filevine and every other legal platform in which legal professionals are using AI to draft legal documents that rely on legal citations.<\/p>\n Thanks to concerns about AI accuracy and rampant hallucinations<\/a>, the role \u2013 or maybe I should say the place \u2013 of the citator is evolving.<\/p>\n For most of their history, citators were legal research products \u2013 the last step before you wrapped up your research. But, as Anderson argued in our briefing, citation validation is now a required step in any legal workflow that produces a document relying on case law.<\/p>\n \u201cUsually you\u2019re taking facts, applying them to law and drafting,\u201d he said. \u201cThat is the day-to-day shoe leather work of a lawyer.\u201d<\/p>\n Filevine already held the facts, he said, but the missing pieces were a case law corpus and a way to confirm that what the corpus returns is still good law.<\/p>\n \u201cAnd I think now there\u2019s another step,\u201d he said, \u201cwhich is make sure nothing you\u2019ve looked at is hallucinated.\u201d<\/p>\n Earlier this year, at a meeting of roughly 20 large firms that Filevine convened, Anderson heard the same anxiety about hallucinations expressed repeatedly. One litigator said his top-10 firm now requires three separate sign-offs before any filing goes out, with the briefing associate required to attest that the associate had checked every citation and every holding.<\/p>\n So what is Filevine\u2019s answer to this need? In our briefing this week, Anderson and Rizner demonstrated how the brief auditor and citator work.<\/p>\n For the brief auditor, after It ingests a document, it extracts and analyzes every citation, and then reports four things in a side-by-side chart:<\/p>\n Using briefs pulled from PACER in matters where courts had already found problems, Anderson showed me examples. In one, a brief asserted that the 11th<\/sup> Circuit had squarely held that \u201c100% healed\u201d policies violate the ADA. The tool reported that the phrase appears in the opinion only in the plaintiff\u2019s own request to return to full duty.<\/p>\n In another, drawn from Knight v. Baptist Hospital of Miami<\/em>, the brief cited a passage for the proposition that disparate discipline of similarly situated employees is evidence of pretext. The tool flagged that the quoted sentence does not appear in the opinion and that the court\u2019s reasoning runs the other way, having found the comparator not similarly situated.<\/p>\n \u201cIt\u2019s really quite remarkable how subtle these hallucinations can be even when the case itself is not hallucinated,\u201d he said. He noted that fabricated support often turns up in a dissent or in a recitation of case history rather than in the holding.<\/p>\n The citator works differently from a traditional one. Rather than starting from a case and examining its citation graph, the user highlights the specific language at issue.<\/p>\n Filevine then runs two passes \u2013 a traversal of the citation graph and a semantic similarity search \u2013 across its corpus for opinions using comparable reasoning. Opinions that come up as likely candidates are handed to LLMs, which distill the conflicts.<\/p>\nThe Challenge Of Citators<\/strong><\/h3>\n
Citators As An Essential Tool<\/strong><\/h3>\n
Filevine\u2019s Answer to This Need<\/strong><\/h3>\n
\n
![\"\"](\"https:\/\/i0.wp.com\/www.lawnext.com\/wp-content\/uploads\/2026\/09\/Filevine-hallucination-checker-1024x476.png?resize=1024%2C476&ssl=1\" "\\"\\"")
<\/a><\/p>\nA Different Kind Of Citator<\/strong><\/h3>\n
![\"\"](\"https:\/\/i0.wp.com\/www.lawnext.com\/wp-content\/uploads\/2026\/09\/Filevine-Demo-Citator-1024x551.png?resize=1024%2C551&ssl=1\" "\\"\\"")
<\/a><\/p>\n![\"\"](\"https:\/\/i0.wp.com\/www.lawnext.com\/wp-content\/uploads\/2026\/09\/Filevine-hallucination-checker-results-1024x565.png?resize=1024%2C565&ssl=1\" "\\"\\"")
<\/a><\/p>\n