Fri. Mar 29th, 2024

Extract from Technology Assisted Review TAR Guidelines Shared Under Creative Commons License via EDRM (EDRM.net)

Technology Assisted Review (TAR) is useful for many tasks within the Electronic Discovery Reference Model (EDRM), with one of its central applications being its use in determining the relevancy of documents in the review stage of eDiscovery in support of document production obligations.

Highlighted in the recently published EDRM/Duke Technology Assisted Review Guidelines, a defensible TAR workflow for supporting relevant and non-relevant document classification in the eDiscovery review process addresses the following nine components:

  • Identification of the team to finalize and engage in the workflow
  • Selection of the software
  • Identification, analysis, and preparation of the TAR set
  • Development of project schedule and deadlines
  • Human reviewer preparation for engaging in TAR
  • Human reviewer training of the computer to detect relevancy, and the computer classification of the set of documents
  • Implementation of review quality control measures during training
  • Determination of when computer training is complete and validate
  • Final identification, review, and production of the predicted relevant set

To engage in the management of this important workflow, the producing party needs access to TAR software. The decision on what software to use goes hand-in-hand with the service provider selection.

A key element to ensuring a successful project is a service provider who will be assisting or managing the process. The producing party needs to perform due diligence on the service provider selection. The service provider should have an expert who can describe the process in a meaningful and understandable way, including the steps that the team will need to take to ensure a reasonable review. Other topics that the producing party might consider discussing with the service provider are:

  • Does the service provider have a written TAR guide?
  • Which TAR software does the service provider have?
  • Can the service provider demonstrate by using measurable verification
    methods that the software they use works for the particular assigned task?
  • How many TAR-based reviews in support of production obligations has the service provider completed in the past six months or year? What were the results?
  • Has the service provider ever provided affidavits or declarations in support of the workflow?
  • How does the service provider report on the progress or provide updates on the workflow?
  • What level of training and support will the service provider provide to the
    team?
  • Does the service provider have an expert that is able to support or participate in discussions with the opposing party or the court on the use of TAR?
  • If supplemental collections or rolling productions are anticipated throughout TAR, how will that impact the workflow?
  • If foreign language is at issue, how will foreign language documents be handled?
  • Who will be reviewing and coding the training documents, and where does that review take place?
  • What factors or criteria are assessed to determine whether the workflow is reasonable?
  • Is the TAR software actively supported? (Does the software provider periodically engage in upgrades, updates, and bug fixes to improve the software and workflow?)

To learn more about the important and extensive guidelines on TAR as shared by EDRM/Duke, please read the complete announcement on EDRM/Duke TAR Guidelines, review the downloadable (PDF) version of the TAR Guidelines, and read the TAR Guidelines Q&A with John Rabiej, Deputy Director of the Bolch Judicial Institute at Duke Law.

Full Text of Guidelines as Shared Under Creative Commons License via EDRM (EDRM.net).

TAR-Guidelines-Final

Additional Reading

Source: ComplexDiscovery

 

Generative Artificial Intelligence and Large Language Model Use

ComplexDiscovery OÜ recognizes the value of GAI and LLM tools in streamlining content creation processes and enhancing the overall quality of its research, writing, and editing efforts. To this end, ComplexDiscovery OÜ regularly employs GAI tools, including ChatGPT, Claude, Midjourney, and DALL-E, to assist, augment, and accelerate the development and publication of both new and revised content in posts and pages published (initiated in late 2022).

ComplexDiscovery also provides a ChatGPT-powered AI article assistant for its users. This feature leverages LLM capabilities to generate relevant and valuable insights related to specific page and post content published on ComplexDiscovery.com. By offering this AI-driven service, ComplexDiscovery OÜ aims to create a more interactive and engaging experience for its users, while highlighting the importance of responsible and ethical use of GAI and LLM technologies.

 

Have a Request?

If you have information or offering requests that you would like to ask us about, please let us know, and we will make our response to you a priority.

ComplexDiscovery OÜ is a highly recognized digital publication focused on providing detailed insights into the fields of cybersecurity, information governance, and eDiscovery. Based in Estonia, a hub for digital innovation, ComplexDiscovery OÜ upholds rigorous standards in journalistic integrity, delivering nuanced analyses of global trends, technology advancements, and the eDiscovery sector. The publication expertly connects intricate legal technology issues with the broader narrative of international business and current events, offering its readership invaluable insights for informed decision-making.

For the latest in law, technology, and business, visit ComplexDiscovery.com.