Explore these questions and answers to gain a deeper understanding of how Lexis+ AI can streamline your legal processes and enhance your legal workflow.
- Allows customers to interact with Lexis+ AI like they would with a trusted colleague who intelligently and conversationally responds to their requests.
- Simplifies the complex and time-consuming legal research journey, providing a search experience for diverse legal questions with citations, facilitating lawyers’ ability to complete research effectively and efficiently.
- Choose what you want to draft, enter your prompt, and Lexis+ AI will quickly produce a reliable draft using leading legal content that you can edit with your expertise, generating a first draft of a legal document, and allowing users to change the language and tone from a simple prompt.
- Generates client emails, letters, legal memos, arguments and contract clauses with remarkable speed and ease.
- Provides a custom summary of any case law document to speed up and guide insightful analysis on a case.
- Offers accurate & complete legal summaries in seconds without clicking into a single search result.
- Upload your existing document(s) to summarize, compare and/or semantically search through Lexis+ AI.
- Allows customers to find facts related to a given legal issue, find cases and statutes that have been mentioned in the documents and interpret terms of art.
Lexis+ AI leverages generative AI to engage with users and assist in the completion of a research or drafting task. It uses a neural network architecture to analyze and understand natural language input and generate appropriate responses based on LexisNexis data. This experience allows for a dynamic, conversational, and iterative research process, contrasting with the more linear and potentially frustrating nature of traditional research.
A user’s conversation history is available for 90 days. Customer information is encrypted while in storage and users can delete chat histories to remove them from their stored user history.
We recommend that you use the 5P Prompting Methodology to get the best outcome. The 5Ps are: Prime, Persona, Prompt, Product, and Polish. For more information, please see our Prompting User Guide.
Yes. A jurisdiction filter is available in Lexis+ AI.
ChatGPT is not suited for legal research as it does not meet the high standards of accuracy and completeness required for this work. Lexis+ AI is grounded in our extensive repository of authoritative and exclusive Canadian legal content and use cases, which is something that Chat GPT does not have access to. ChatGPT does not employ techniques like Retrieval Augmented Generation (RAG) to ground its output in truth.
All Lexis+ AI conversations, including queries input by users, will be encrypted in transit and at rest. Conversations are removed from the user’s chat history after 90 days. Users also have individual control of prompt history and option to delete their prompt history manually. Lexis+ AI adheres to the same security architecture, reviews, audits, and validation processes as Lexis+ Canada and all our other online solutions. The generative AI capabilities have been engineered and deployed to meet our high-level security standards, with a key focus on protecting and segmenting customer activity.
LexisNexis DOES NOT use customer data to tune or train the models for Lexis+ AI or any other online solution. Users have control over their prompt history and are able delete all their history manually.
Lexis+ AI leverages our unparalleled collection of Canadian legal content, which enables us to provide linked legal citations and supporting references for responses which help reduce risk of hallucinations. Lexis+ AI is designed to minimize hallucinations by incorporating Retrieval Augmented Generation (RAG) techniques which act as guardrails to identify and validate the most relevant potential output. In addition, our "humans-in-the-loop" testing process uses a team of specially trained legal experts who evaluate language model output to likely user prompts for consistency and quality.
We employ a “humans-in-the-loop” approach where subject matter experts, data scientists, and engineers are evaluating prompt responses and identifying adjustments. This is done in addition to the adjustments made based upon direct user feedback, highlighting a good or bad output within Lexis+ AI.
While Lexis+ AI aims to provide accurate outputs, users must verify the responses, especially in a legal context where accuracy is critical. Legal professionals remain solely responsible for ensuring their work product is competently produced and verifiable.
Lexis+ AI is fully supported by our Product Adoption & Learning (PAL) Team who provide free, in-person and virtual training sessions as well as online training videos and documentation. Visit the Lexis+ AI Training Resources page to view the training calendar and other available resources.
Like the world of LLMs, our capabilities are evolving quickly. We anticipate many new capabilities and welcome customer feedback on potential applications of this new technology.
Lexis+ AI is grounded in comprehensive, trusted LexisNexis content sources including:
- Primary Law
- Proprietary Secondary Sources
- Practical Guidance Materials
- Legal Encyclopedic Works including Halsbury’s® Laws of Canada
We are taking a multi-model approach, which allows us to be flexible as new and better technologies emerge. This approach is rooted in large-scale commercial cloud vendors like Microsoft® Azure and Amazon Bedrock. Different models are better suited to different use cases, so we use the best model for the appropriate use case.
Lexis+ AI excels at providing the most accurate answers to legal inquiries because of:
- Global authoritative content current through the day’s development as customers would expect from LexisNexis.
- Proprietary search technology that allows us to improve model responses and integrated trusted content from Lexis+.
- Human legal experts in the loop, as we leverage a substantial group of legally trained professionals that continuously improve model performance.
- Latest generative AI models that are selected because of their performance against specific legal use cases.
- A deep bench of legal AI engineering and data science talent, deeply informed about legal market use cases
Secure and private interaction is our highest priority.
- The Lexis+ AI solution is built with an emphasis on Privacy by Design, a set of standards that ensure user activity and model interactions are limited to the individual.
- Our generative AI is a private model, not shared with third parties. This means that users sessions are always secure.
- Lexis+ AI is built and deployed via commercial-grade cloud infrastructure. This infrastructure means that we can manage performance and security, while also leveraging cutting-edge development from providers like Microsoft Azure and AWS to deliver secure models for commercial customers.
- Lastly, our development of Lexis+ AI is guided by a curated set of Responsible AI Principles. RELX, our parent company, is a leader in the thinking about how AI should be leveraged with an emphasis on transparency in development and bias-free implementation.