A legal research tool that tracks the subsequent history and treatment of a case or statute, enabling lawyers to confirm whether authority remains valid and binding.
Last reviewed: 2026/05/19
AI legal research pioneer (CARA AI); standalone retired 2025, its technology now powers Thomson Reuters CoCounsel.
AI-powered legal research with citation-validated answers from Westlaw.
Conversational legal research with real-time Shepard's citation validation.
Move from this definition to role-based legal AI shortlists and the selection criteria that matter for each type of legal team.
Am Law 200 and global firm workflows: accuracy at scale, security compliance, and matter-level auditability.
Last reviewed: 2026/05/19. Definitions are written by the LawyerAI Editorial team. Commercial relationships are disclosed and do not determine editorial scores or conclusions. See our Sponsorship & Affiliate Disclosure.
A citator is a legal reference tool that tracks the subsequent history and judicial treatment of a case, statute, regulation, or other legal authority. For case law, a citator shows every later decision that has cited the original case, along with the nature of the treatment — whether the later court followed, distinguished, criticized, limited, overruled, or otherwise addressed the earlier holding. This function allows lawyers to verify that a case they plan to cite remains valid authority and has not been negatively affected by subsequent decisions.
The two dominant commercial citator systems in U.S. legal research are Shepard's Citations (LexisNexis) and KeyCite (Westlaw). Both assign signal indicators — colored flags or letters — that alert researchers to negative treatment: a red signal typically indicates the case has been overruled or is otherwise problematic authority; a yellow signal flags caution; a green signal indicates positive treatment. These signals represent editorial judgments layered on top of the underlying citation data.
Citators serve an additional function beyond validity checking: they enable lawyers to find cases that have cited and discussed the original case, which is a powerful tool for locating additional relevant authority on a legal issue. A landmark case on a legal principle may have been cited hundreds of times; the citator reveals which of those subsequent cases have engaged most deeply with the principle, helping researchers identify the most relevant recent developments.
Citing overruled or negatively treated authority in a brief is a professional responsibility issue, not merely a tactical problem. Courts and opposing counsel routinely check citations, and filing papers that rely on bad law reflects poorly on the lawyer and may draw sanctions. Citator verification is therefore a non-negotiable step in brief-writing and opinion-drafting — no authority should be cited without confirming its current validity.
The competency implications of AI-generated legal research make citator verification even more important. Large language models used in legal research can hallucinate case citations — generating plausible-sounding citations to cases that do not exist — or cite cases for propositions they do not actually stand for. When AI assists in legal research, citator verification must be applied to every case the AI identifies before the lawyer relies on it. The AI hallucination problem in legal research is well-documented, and citator checking is one of the primary safeguards.
For statutory research, citators track statutory amendments, regulatory changes, and judicial interpretations that affect a statute's current meaning and application. A statute that was good law when a form document was drafted may have been amended, interpreted narrowly, or partially invalidated since then. Citator verification of statutory citations prevents reliance on outdated legal frameworks.
Westlaw Precision AI and Lexis+ AI have integrated citator functionality directly into their AI-assisted legal research workflows. When these tools generate responses citing case law, they include citator signals alongside the citations, allowing lawyers to see at a glance whether cited authority has been negatively treated without running a separate citator check. This integration reduces the risk that AI-generated research bypasses the validity-checking step.
Casetext's CoCounsel and similar tools built on AI research capabilities similarly surface negative treatment indicators when presenting case citations. Some tools go further, proactively flagging if a case the lawyer mentions in a query has been overruled or limited — catching errors before they are incorporated into work product.
AI is also being applied to the underlying citator function itself: analyzing the text of citing opinions to determine the nature of treatment more precisely than keyword-based classification. Traditional citators rely on editorial classification, which can be incomplete or inconsistent; NLP-based treatment analysis can potentially identify the specific passage of the cited case being addressed, the legal issue to which it is applied, and whether the treatment is positive or negative in context.