Explore

Alphabet Soup: TAR, CAL, and Assisted Review, Assisted Review Series Part 1

1 / 9

Over the nine years since it first rose to prominence in eDiscovery, technology-assisted review has expanded to include new tools, more workflows, and a variety of legal issues


TAR first rose to prominence in the legal industry around 2011 under the name predictive coding.  In that year, the first few discovery-oriented TAR solutions were in use. Recommind, received a patent for its predictive coding process (after attempting to trademarkpredictive coding”), and discussion of the technology’s potential to transform legal practice spread from industry press to mainstream media outlets.

The Rise of Predictive Coding

Over the nine years since, phrase predictive coding largely was abandoned in favor of the more generic term TAR – or, sometimes, computer-assisted review (CAR). TAR and CAR have also been joined by TAR 2.0 and by CAL (continuous active learning), while LSI and PLSA have been joined by SVM and other new acronyms.  Over that same time period, every major provider of eDiscovery review software or services has joined Recommind (now OpenText) in developing or licensing assorted technology-assisted review solutions for their clients to use.

Despite the rapid evolution of the available solutions, TAR adoption by practitioners was not as rapid or as widespread as many hoped, but it has continued to steadily grow:

  • Four years ago, Recommind found itself on the other side of the table challenging patents and trademarks related to CAL filed by others
  • Three years ago, the U.S. Department of Justice updated its Model Second Request to incorporate new guidance on the use of TAR in responding to such requests, and The Sedona Conference published a new TAR Case Law Primer
  • Two years ago, high-profile cases were still turning to TAR to handle large data volumes, such as those in the Michael Cohen case (in which TAR was proposed for privilege review)
  • Last year, the EDRM organization published a new guidelines document covering the use of TAR in eDiscovery

And, as TAR’s adoption has grown, case law exploring issues with TAR usage has continued to accumulate.  From 2012’s da Silva Moore, to 2020’s In re Mercedes-Benz, courts have wrestled with whether and when TAR is okay, if it can be required, what processes should be employed when it is used, and more.

The Challenges of Evolution 

All of this rapid technical and legal evolution has made it challenging for practitioners to get a simple handle on TAR and what it means for their matters.  Common questions include:

  • What do all those terms mean and which ones do I really need to know?
  • What are the different approaches, and which make sense when?
  • How does TAR’s quality compare to traditional review quality?
  • Do I need permission to use it? Can I be compelled to use it?
  • What about process transparency and objections?
  • What about using search terms and TAR?

The uncertainty surrounding these questions and others is, in part, responsible for the slower than predicted adoption of these approaches in eDiscovery.

About this Series

In this series, we will explore the answers to these questions and others to better equip you to leverage TAR in your matters.  We will begin with an explication of key terms, core concepts, and their applications to address the what; then, we will turn to relative quality and cost to address the why; and, finally, we will turn to the relevant case law to explore the when and the how.

A Note about Terminology

Throughout this series, we will use technology-assisted review and TAR as generic, umbrella terms that encompass all approaches in which some form of computer review is used to either extend or replace some amount of human review.  For example:

  • Categorization, predictive coding, continuous active learning, and other approaches are all different forms of TAR
  • LSI, PLSA, SVM, and other variations are all mathematical approaches underpinning different forms of TAR

We will use the narrower names for these particular workflows, tools, and underlying mathematical approaches whenever we are discussing them specifically, and we will use TAR whenever we are speaking generally about the whole class of approaches.


About the Author

Matthew Verga

Director of Education

Matthew Verga is an electronic discovery expert proficient at leveraging his legal experience as an attorney, his technical knowledge as a practitioner, and his skills as a communicator to make complex eDiscovery topics accessible to diverse audiences. A thirteen-year industry veteran, Matthew has worked across every phase of the EDRM and at every level from the project trenches to enterprise program design. He leverages this background to produce engaging educational content to empower practitioners at all levels with knowledge they can use to improve their projects, their careers, and their organizations.

Whether you prefer email, text or carrier pigeons, we’re always available.

Discovery starts with listening.

(877) 545-XACT / or / Subscribe for Updates